© 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. 123519
    Prev
    Next
    INDEX
    Explanations

    data tables

    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
    楒
    -0.07
    "To
    -0.07
    ật
    -0.07
    蝴蝶
    -0.07
    瀑布
    -0.07
    ampoo
    -0.07
    我的
    -0.07
    דף
    -0.07
    又是
    -0.06
    篌
    -0.06
    POSITIVE LOGITS
     Leon
    0.07
    族
    0.07
    奏
    0.07
    赴
    0.07
     Opposition
    0.07
     congregation
    0.07
    _periods
    0.07
    一族
    0.07
     bureaucracy
    0.06
     Milwaukee
    0.06
    Activations Density 0.013%

    No Known Activations