© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29617
    Prev
    Next
    INDEX
    Explanations

    constitutional

    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
    介入
    -0.07
     даль
    -0.07
     SA
    -0.07
    结尾
    -0.07
    جهاد
    -0.07
    铷
    -0.07
    瞬间
    -0.07
    aghan
    -0.06
    изация
    -0.06
    ╁
    -0.06
    POSITIVE LOGITS
    borg
    0.07
    YO
    0.07
     Wolf
    0.07
    Girls
    0.07
    orte
    0.07
    born
    0.07
    ür
    0.07
    붕
    0.06
    羟
    0.06
    posables
    0.06
    Activations Density 0.002%

    No Known Activations