© 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. 29337
    Prev
    Next
    INDEX
    Explanations

    life, career, properties, history, usage

    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
    ugi
    -0.06
    ilt
    -0.06
    æѤæĸĩ
    -0.06
     consign
    -0.06
    ernih
    -0.06
    pn
    -0.06
    err
    -0.06
    为ä¹ĭ
    -0.06
    endr
    -0.06
    çķ
    -0.06
    POSITIVE LOGITS
    é¦ĸåħĪ
    0.08
    dex
    0.08
    fatt
    0.08
    кÑĥлÑĮÑĤ
    0.08
    ×ijק
    0.08
    诽
    0.08
    é¦ĸåħĪåľ¨
    0.08
    é¦ĸåħĪè¦ģ
    0.08
    ẩm
    0.08
    é¦ĸåħĪéľĢè¦ģ
    0.07
    Activations Density 0.142%

    No Known Activations