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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 87903
    Prev
    Next
    INDEX
    Explanations

    say #include

    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
     Oz
    -0.08
     Serve
    -0.07
    cluir
    -0.07
     Dez
    -0.07
    蛏
    -0.07
     loginUser
    -0.07
    崃
    -0.07
     Hmm
    -0.07
    建て
    -0.07
     Dess
    -0.07
    POSITIVE LOGITS
    .Disabled
    0.07
     material
    0.07
    Material
    0.07
    社会保险
    0.07
    声誉
    0.07
    _people
    0.07
    _story
    0.07
    大众
    0.07
     pressing
    0.07
     shed
    0.07
    Activations Density 0.009%

    No Known Activations