© 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. 15-RESID-POST-AA
    11. 123600
    Prev
    Next
    INDEX
    Explanations

    licensed

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WEST
    -0.08
    砄
    -0.07
    lore
    -0.07
     characterize
    -0.06
    elm
    -0.06
    中国特色
    -0.06
     worthwhile
    -0.06
    resume
    -0.06
     Bộ
    -0.06
    imbledon
    -0.06
    POSITIVE LOGITS
     Christmas
    0.07
     Ottoman
    0.07
     remnants
    0.07
    _g
    0.07
    شاء
    0.07
    reeting
    0.07
    肢体
    0.06
    集结
    0.06
    置业
    0.06
     ведь
    0.06
    Activations Density 0.453%

    No Known Activations