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. 7360
    Prev
    Next
    INDEX
    Explanations

    The

    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
    GBP
    -0.07
    Cold
    -0.07
     HTTPS
    -0.06
    微软
    -0.06
     suffice
    -0.06
     memorable
    -0.06
    沃尔沃
    -0.06
     deficits
    -0.06
    FullYear
    -0.06
    גידול
    -0.06
    POSITIVE LOGITS
     weren
    0.08
    ألم
    0.07
     tray
    0.07
     Mater
    0.07
    _le
    0.06
     וא
    0.06
     tens
    0.06
     INTERNAL
    0.06
     aa
    0.06
    (train
    0.06
    Activations Density 0.009%

    No Known Activations