© 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. 41050
    Prev
    Next
    INDEX
    Explanations

    by

    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
     Check
    -0.08
    尝试
    -0.07
     OPTION
    -0.07
    <|im_start|>
    -0.07
    手続き
    -0.06
    雇佣
    -0.06
     الآ
    -0.06
     Learn
    -0.06
    	queue
    -0.06
     proceed
    -0.06
    POSITIVE LOGITS
    Suffix
    0.07
     location
    0.07
    (disposing
    0.07
    -property
    0.06
     interpret
    0.06
     cüm
    0.06
     RCS
    0.06
    科研院所
    0.06
     Caption
    0.06
    _I
    0.06
    Activations Density 0.042%

    No Known Activations