© 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. 25847
    Prev
    Next
    INDEX
    Explanations

    Code or numbers

    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
     point
    -0.07
    统筹推进
    -0.07
    paramref
    -0.07
     Zoom
    -0.07
     PackageManager
    -0.07
    DevExpress
    -0.07
     Dayton
    -0.07
     seasoned
    -0.07
    UseProgram
    -0.07
    (indexPath
    -0.07
    POSITIVE LOGITS
    Number
    0.07
    🤨
    0.07
     loving
    0.07
     kas
    0.06
    yre
    0.06
    abled
    0.06
     över
    0.06
    etrics
    0.06
     số
    0.06
    grily
    0.06
    Activations Density 0.053%

    No Known Activations