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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24661
    Prev
    Next
    INDEX
    Explanations

    informal writing separators

    np_max-act · gemini-2.0-flash

    Spots the start of a quoted/example response or the opening quotation mark that begins a sample reply.

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     вып
    -0.07
     tee
    -0.07
    諮
    -0.06
     Św
    -0.06
    .mov
    -0.06
    монтаж
    -0.06
     prelim
    -0.06
    �
    -0.06
    诸葛
    -0.06
     indicates
    -0.06
    POSITIVE LOGITS
    	ui
    0.07
    LM
    0.07
     Level
    0.07
    בי
    0.07
    _products
    0.07
    /context
    0.06
     Blessed
    0.06
     armies
    0.06
     Growth
    0.06
    Admin
    0.06
    Activations Density 0.109%

    No Known Activations