© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 123016
    Prev
    Next
    INDEX
    Explanations

    person

    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
    cales
    -0.09
    _UPDATE
    -0.08
    解釋
    -0.08
    ⏯
    -0.07
     mở
    -0.07
     grappling
    -0.07
     raids
    -0.07
     dừng
    -0.07
    基调
    -0.07
     revisit
    -0.07
    POSITIVE LOGITS
    人
    0.07
    𝑘
    0.07
    поз
    0.07
     Temper
    0.07
    pics
    0.07
    塑料
    0.06
     конструк
    0.06
    енко
    0.06
    דמות
    0.06
    פות
    0.06
    Activations Density 0.072%

    No Known Activations