© 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. 22657
    Prev
    Next
    INDEX
    Explanations

    correlation coefficient, ratio, percentages, values

    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
    бÑĢи
    -0.08
    åĴ¨è¯¢æľįåĬ¡
    -0.08
     replacements
    -0.07
    زاÙħ
    -0.07
    以ä¸ĭæŃ¥éª¤
    -0.07
    稳
    -0.07
    -direct
    -0.07
     заменÑĥ
    -0.07
    Ñģил
    -0.07
    owani
    -0.07
    POSITIVE LOGITS
    centage
    0.07
    kar
    0.07
    è´Ł
    0.06
     Ratio
    0.06
    表æĺİ
    0.06
    onta
    0.06
    hör
    0.06
    è¿Ļ表æĺİ
    0.06
    æ¯Ķä¾ĭ
    0.06
    æ¯Ķä¾ĭ为
    0.06
    Activations Density 0.052%

    No Known Activations