© 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. 86871
    Prev
    Next
    INDEX
    Explanations

    :

    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
     pops
    -0.07
    一波
    -0.07
     drought
    -0.07
    TASK
    -0.06
    VILLE
    -0.06
    addChild
    -0.06
    ימות
    -0.06
    unicipio
    -0.06
     Clemson
    -0.06
     ActionResult
    -0.06
    POSITIVE LOGITS
    苦恼
    0.08
    fea
    0.07
     kb
    0.07
    醚
    0.07
    移到
    0.07
    /apple
    0.07
    丹麦
    0.06
    揭露
    0.06
     Ending
    0.06
    �
    0.06
    Activations Density 0.001%

    No Known Activations