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. 11-RESID-POST-AA
    6. 1791
    Prev
    Next
    INDEX
    Explanations

    EpiPen

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prus
    -0.07
    害
    -0.07
    侥
    -0.07
    RF
    -0.07
     Tunisia
    -0.07
     qx
    -0.06
    费
    -0.06
    rens
    -0.06
    _save
    -0.06
     jugar
    -0.06
    POSITIVE LOGITS
     экран
    0.07
    }>↵
    0.07
     skulls
    0.07
    𫫇
    0.06
    (selected
    0.06
    骁
    0.06
    /device
    0.06
    .offsetTop
    0.06
    (chart
    0.06
    麒麟
    0.06
    Activations Density 0.001%

    No Known Activations