© 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. 58309
    Prev
    Next
    INDEX
    Explanations

    trailing characters

    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
    jew
    -0.08
    çīĮçļĦ
    -0.08
    leti
    -0.07
    .prototype
    -0.07
    åĴĮç»´çĶŁç´ł
    -0.07
    ä¸Ĭçĺ¾
    -0.07
    orti
    -0.07
    uç
    -0.06
    ä¸İä¿¡æģ¯
    -0.06
    ä»ĬåIJİçļĦ
    -0.06
    POSITIVE LOGITS
    most
    0.09
    -most
    0.08
     zeros
    0.08
    åŃľ
    0.08
    /back
    0.07
    /off
    0.07
    _zeros
    0.07
    marsh
    0.07
    /app
    0.07
    ÙĬاÙĦ
    0.07
    Activations Density 0.008%

    No Known Activations