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. 31213
    Prev
    Next
    INDEX
    Explanations

    code arguments

    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
    没人
    -0.07
     HttpResponse
    -0.07
    _decor
    -0.07
    ype
    -0.06
    oyal
    -0.06
    acing
    -0.06
    ல
    -0.06
     eaten
    -0.06
     לכם
    -0.06
    有这样的
    -0.06
    POSITIVE LOGITS
    (em
    0.08
     Mer
    0.08
     미래
    0.08
     между
    0.08
    ürnberg
    0.07
    (edge
    0.07
     Boat
    0.07
     faç
    0.07
    .performance
    0.07
    _ke
    0.07
    Activations Density 0.009%

    No Known Activations