© 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. 60760
    Prev
    Next
    INDEX
    Explanations

    mentioning timeframes

    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
    äºĨ好åĩł
    -0.08
    é¦ĸåħĪåľ¨
    -0.08
    _DU
    -0.07
    æĪĸèĢħæĺ¯
    -0.07
    ierz
    -0.07
    )').
    -0.07
    á»ĵi
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    ä»İä¸Ń
    -0.07
    iaan
    -0.07
    POSITIVE LOGITS
     due
    0.08
     onward
    0.07
    abouts
    0.07
     because
    0.07
    表çݰ为
    0.06
    à¸Ĺะ
    0.06
    /by
    0.06
    .exports
    0.06
    åĴĮåľ¨
    0.06
    due
    0.06
    Activations Density 0.356%

    No Known Activations