© 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. 75392
    Prev
    Next
    INDEX
    Explanations

    Fabrication and cheating

    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
    舸
    -0.07
    FirstChild
    -0.07
    .isConnected
    -0.07
    哪一个
    -0.07
     Lumpur
    -0.06
    istrict
    -0.06
    _UNKNOWN
    -0.06
    想去
    -0.06
    둡
    -0.06
    湖州
    -0.06
    POSITIVE LOGITS
     compliments
    0.07
     sympath
    0.07
     objectId
    0.07
     Variety
    0.07
    9
    0.06
    ╄
    0.06
    .'
    0.06
    .Part
    0.06
     specials
    0.06
     каталог
    0.06
    Activations Density 0.050%

    No Known Activations