Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 27925
    Prev
    Next
    INDEX
    Explanations

    code snippets and file names

    np_max-act · gemini-2.0-flash
    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
    援
    -0.08
     Ars
    -0.07
     proprio
    -0.07
    _DOM
    -0.07
    irable
    -0.07
    _precision
    -0.07
    pricing
    -0.07
     arkadaş
    -0.07
     RJ
    -0.06
    :error
    -0.06
    POSITIVE LOGITS
    앜
    0.07
    تعبير
    0.07
    	actual
    0.07
     muttered
    0.07
    清洗
    0.06
     Potion
    0.06
    At
    0.06
    修剪
    0.06
    .sha
    0.06
     Characters
    0.06
    Activations Density 0.078%

    No Known Activations