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. 19-RESID-POST-AA
    6. 87820
    Prev
    Next
    INDEX
    Explanations

    database queries

    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
    _so
    -0.08
     הנ
    -0.07
     MUCH
    -0.07
     crop
    -0.07
     vacc
    -0.07
     ware
    -0.07
     pract
    -0.07
     ostr
    -0.07
     Cup
    -0.07
     dific
    -0.07
    POSITIVE LOGITS
    الة
    0.08
    ations
    0.07
     total
    0.06
    🌈
    0.06
    ิด
    0.06
    ROID
    0.06
    -total
    0.06
    erguson
    0.06
    ingga
    0.06
    遭遇
    0.06
    Activations Density 0.003%

    No Known Activations