© 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. 37982
    Prev
    Next
    INDEX
    Explanations

    adsbygoogle.push

    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
    _DEFINED
    -0.07
    pte
    -0.07
    rapper
    -0.07
    æĹ¥ä¸Ĭ
    -0.06
    ste
    -0.06
     ÙĪÙĩÙĥذا
    -0.06
    IRA
    -0.06
    ÅĦczy
    -0.06
    ä¸Ĭ马
    -0.06
    obel
    -0.06
    POSITIVE LOGITS
    arged
    0.07
    ExecutionContext
    0.07
    èªĬ
    0.07
    eldes
    0.07
    ERSHEY
    0.06
    çīĪæĿĥä¸İåħį责声æĺİ
    0.06
    .promise
    0.06
    Ïģγ
    0.06
    ÑĥÑĤ
    0.06
    çݯå¢ĥä¼ĺç¾İ
    0.06
    Activations Density 0.012%

    No Known Activations