© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 24658
    Prev
    Next
    INDEX
    Explanations

    holes

    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
    生生
    -0.07
    酷
    -0.07
    (tr
    -0.07
    =$("#
    -0.07
    Ton
    -0.07
    Add
    -0.06
    ................................
    -0.06
    .Display
    -0.06
    淹没
    -0.06
    㮾
    -0.06
    POSITIVE LOGITS
    各国
    0.07
    _orders
    0.07
    rote
    0.07
     dames
    0.07
    Requests
    0.07
    .Logging
    0.07
     veces
    0.07
     الدول
    0.07
    ancies
    0.07
     -----↵
    0.07
    Activations Density 0.015%

    No Known Activations