© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 102811
    Prev
    Next
    INDEX
    Explanations

    使用

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nắm
    -0.08
     تس
    -0.07
    ﺗ
    -0.07
    .tbl
    -0.07
     Planned
    -0.07
     accountable
    -0.06
    -nil
    -0.06
    还得
    -0.06
     Epstein
    -0.06
     scape
    -0.06
    POSITIVE LOGITS
    使用
    0.10
     使用
    0.08
    聚合
    0.08
     comentario
    0.08
    (language
    0.08
     />
    ↵
    0.07
     Savage
    0.07
    /detail
    0.07
    ();↵↵↵
    0.07
     Robert
    0.07
    Activations Density 0.006%

    No Known Activations