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. 85645
    Prev
    Next
    INDEX
    Explanations

    ER

    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
    serviceName
    -0.07
    те
    -0.07
    setWidth
    -0.06
    tplib
    -0.06
    .D
    -0.06
    Notifications
    -0.06
    看好
    -0.06
     completing
    -0.06
    ImageView
    -0.06
    IllegalAccessException
    -0.06
    POSITIVE LOGITS
    /png
    0.08
     Enums
    0.07
    ERGY
    0.07
    .loc
    0.07
     CRS
    0.07
     לעשות
    0.07
    贬
    0.07
    �
    0.07
    藍
    0.07
    -points
    0.07
    Activations Density 0.041%

    No Known Activations