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. 130557
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    _zoom
    -0.08
     profit
    -0.07
    /utils
    -0.07
    حرية
    -0.07
     debate
    -0.06
    에는
    -0.06
    很多时候
    -0.06
    ading
    -0.06
    .pool
    -0.06
    #af
    -0.06
    POSITIVE LOGITS
     Couldn
    0.07
    𫫇
    0.07
    ASCADE
    0.07
    igi
    0.07
     santé
    0.07
    QUI
    0.07
     Perkins
    0.07
     handset
    0.07
    鄰
    0.07
    "},
    ↵
    0.06
    Activations Density 0.151%

    No Known Activations