© 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. 21972
    Prev
    Next
    INDEX
    Explanations

    repulsive

    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
    _forward
    -0.07
    -age
    -0.07
    athom
    -0.07
    .permission
    -0.07
    弩
    -0.07
    =d
    -0.06
    ax
    -0.06
    /disc
    -0.06
    config
    -0.06
    Domain
    -0.06
    POSITIVE LOGITS
     Москва
    0.07
    医护人员
    0.07
    战斗力
    0.07
     physicians
    0.07
     swung
    0.07
    ។
    0.07
    :bg
    0.07
    .vertx
    0.07
    RTOS
    0.06
    벤
    0.06
    Activations Density 0.005%

    No Known Activations