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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 14338
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ис
    -0.08
    Choosing
    -0.07
    heiten
    -0.07
    奢
    -0.07
    _SCL
    -0.07
    /cl
    -0.07
     interf
    -0.07
    蹒
    -0.07
    gunakan
    -0.07
    索赔
    -0.07
    POSITIVE LOGITS
    靓
    0.06
    عرو
    0.06
    껐
    0.06
     cave
    0.06
     Wyatt
    0.06
    (LayoutInflater
    0.06
    少爷
    0.06
    源头
    0.06
     Variation
    0.06
    توقيع
    0.06
    Activations Density 0.003%

    No Known Activations