© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 129723
    Prev
    Next
    INDEX
    Explanations

    Instructions or guidelines

    np_max-act · gemini-2.0-flash

    instruction-style framing words and phrases that set writing task parameters (e.g., "write", length/style directives, "with the following aspects", "should", "use", and similar prompt-specifying tokens").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     novel
    -0.07
    ADV
    -0.07
    结晶
    -0.07
     deletes
    -0.07
    _cons
    -0.07
    虓
    -0.07
    	menu
    -0.07
    硎
    -0.06
    当然是
    -0.06
     visual
    -0.06
    POSITIVE LOGITS
    .herokuapp
    0.07
     shady
    0.07
    (port
    0.07
    四处
    0.06
    (wrapper
    0.06
    យ
    0.06
     TOUR
    0.06
    _framework
    0.06
    	wp
    0.06
    _methods
    0.06
    Activations Density 0.097%

    No Known Activations