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. 22959
    Prev
    Next
    INDEX
    Explanations

    Foundation

    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
    谫
    -0.07
    pickup
    -0.07
    xce
    -0.07
    🆕
    -0.07
    SSF
    -0.06
    ⏮
    -0.06
    豉
    -0.06
    裛
    -0.06
    旌
    -0.06
    egend
    -0.06
    POSITIVE LOGITS
    關於
    0.07
     clubs
    0.07
     potatoes
    0.07
     villages
    0.07
     dead
    0.07
    一场
    0.07
    .Column
    0.07
     carts
    0.07
     YouTube
    0.07
     rooms
    0.06
    Activations Density 0.002%

    No Known Activations