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. 36311
    Prev
    Next
    INDEX
    Explanations

    https

    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
     floral
    -0.08
    _detalle
    -0.08
     replaces
    -0.08
     pilgr
    -0.07
     sew
    -0.07
    这片
    -0.07
     blues
    -0.07
    (date
    -0.07
     mozilla
    -0.07
     MIC
    -0.07
    POSITIVE LOGITS
    🤦
    0.07
    antanamo
    0.07
    ett
    0.07
    ❯
    0.07
    เป
    0.06
    前端
    0.06
    _('
    0.06
    网易
    0.06
    -$
    0.06
    埤
    0.06
    Activations Density 0.000%

    No Known Activations