© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26514
    Prev
    Next
    INDEX
    Explanations

    select, order by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJİèĢħ
    -0.07
    *sizeof
    -0.07
    ä¸ĭéĿ¢
    -0.07
    Ø·ÙĬ
    -0.06
    ili
    -0.06
    asInstanceOf
    -0.06
    holm
    -0.06
    ohnt
    -0.06
    vasion
    -0.06
    家乡
    -0.06
    POSITIVE LOGITS
    ä¸Ģè¦ģ
    0.08
    ."[
    0.07
    ardown
    0.07
    人åİ»
    0.07
    orden
    0.07
    enÃŃ
    0.07
    enner
    0.07
    okes
    0.07
     chÄĥng
    0.07
    åīįãģĭãĤī
    0.07
    Activations Density 0.110%

    No Known Activations