Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 111049
    Prev
    Next
    INDEX
    Explanations

    school

    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
     eBook
    -0.08
    迎
    -0.08
     Bene
    -0.07
     complex
    -0.07
    ynamic
    -0.07
     IRequest
    -0.07
    iego
    -0.07
     Gust
    -0.07
    /events
    -0.07
    十余
    -0.07
    POSITIVE LOGITS
    高等学校
    0.07
    Aw
    0.07
    �
    0.07
     modalità
    0.07
    ==============↵
    0.07
    網頁
    0.07
     redraw
    0.07
    诰
    0.07
    我校
    0.07
    莪
    0.06
    Activations Density 0.038%

    No Known Activations