© 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. 23890
    Prev
    Next
    INDEX
    Explanations

    just need or want

    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
    缴æİ¥è¿Ľåħ¥
    -0.08
    :\/\/
    -0.07
    .uf
    -0.07
    orda
    -0.07
    å¿ħ究
    -0.07
    缴æİ¥ä¸İ
    -0.07
    æĽ´å¤ļ
    -0.06
     stricter
    -0.06
    åĪĻ以
    -0.06
    zar
    -0.06
    POSITIVE LOGITS
    èĢĮå·²
    0.08
    ç®Ģç®Ģåįķ
    0.08
    说æľī
    0.08
    ç®Ģåįķåľ°
    0.08
     thôi
    0.07
    æĥij
    0.07
    ç²Ĺçķ¥
    0.07
     کاÙģÛĮ
    0.07
    ioned
    0.07
    çľĭèµ·æĿ¥å¾Ī
    0.07
    Activations Density 0.042%

    No Known Activations