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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 48472
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _ue
    -0.08
    分开
    -0.08
    dcc
    -0.07
    bbbb
    -0.07
     rè
    -0.07
    ?type
    -0.07
     Notify
    -0.07
    tty
    -0.07
    outines
    -0.07
    一副
    -0.07
    POSITIVE LOGITS
     Pioneer
    0.07
    십
    0.07
    I
    0.07
    生态保护
    0.07
    伊朗
    0.07
    																			
    0.06
     salmon
    0.06
    이고
    0.06
    יג
    0.06
     {}).
    0.06
    Activations Density 0.048%

    No Known Activations