© 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. 19-RESID-POST-AA
    11. 109667
    Prev
    Next
    INDEX
    Explanations

    thrift

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    停车
    -0.07
     culo
    -0.07
    Verify
    -0.07
    榆林
    -0.07
     miss
    -0.07
    קרא
    -0.07
    打扫
    -0.07
    载
    -0.07
    用餐
    -0.07
     irrespective
    -0.07
    POSITIVE LOGITS
    riority
    0.07
    oble
    0.07
    ович
    0.07
     tgt
    0.07
     б
    0.07
     gs
    0.07
    큠
    0.07
    ogui
    0.06
    ㉱
    0.06
    ʵ
    0.06
    Activations Density 0.006%

    No Known Activations