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. 31198
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     milano
    -0.08
    ถาม
    -0.07
     Uniform
    -0.07
    ᵛ
    -0.07
    úng
    -0.06
    $v
    -0.06
     coy
    -0.06
    욯
    -0.06
    anio
    -0.06
     stares
    -0.06
    POSITIVE LOGITS
    ITIONAL
    0.08
    after
    0.08
     vatanda
    0.07
    birthdate
    0.07
    STE
    0.07
    Phil
    0.07
    _pct
    0.07
    CKET
    0.07
    )][
    0.06
    _db
    0.06
    Activations Density 0.001%

    No Known Activations