© 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. 19-RESID-POST-AA
    11. 109583
    Prev
    Next
    INDEX
    Explanations

    summary or objective

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     withRouter
    -0.08
    吸引更多
    -0.08
     enf
    -0.07
    _UFunction
    -0.07
    更适合
    -0.07
    iddy
    -0.07
     compelling
    -0.07
     hứng
    -0.07
    譬
    -0.07
     impart
    -0.06
    POSITIVE LOGITS
    蜍
    0.08
     GRID
    0.08
    ()>
    0.08
     Histogram
    0.07
    koń
    0.07
    ALLERY
    0.07
    $log
    0.07
     POD
    0.07
    地块
    0.07
     BRO
    0.07
    Activations Density 0.011%

    No Known Activations