© 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. 27050
    Prev
    Next
    INDEX
    Explanations

    diagrams and charts

    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
    displayName
    -0.06
    📖
    -0.06
     notifier
    -0.06
    (Have
    -0.06
    自驾
    -0.06
     ance
    -0.06
    胬
    -0.06
    ניוזלטר
    -0.06
    핌
    -0.06
    ponse
    -0.06
    POSITIVE LOGITS
    inite
    0.07
    位居
    0.07
    譬如
    0.07
    ～↵↵
    0.07
    rk
    0.07
    sup
    0.07
    bo
    0.07
    职业技能
    0.06
     Strat
    0.06
     heaters
    0.06
    Activations Density 0.012%

    No Known Activations