© 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. 57635
    Prev
    Next
    INDEX
    Explanations

    compare, when, characterize

    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
    udet
    -0.08
    çĶ«
    -0.07
     Sole
    -0.07
    éĩijèĬ±
    -0.07
     xì
    -0.06
    åķ¬
    -0.06
    icka
    -0.06
    æ±IJ
    -0.06
     waged
    -0.06
    å®ĮæĪIJåIJİ
    -0.06
    POSITIVE LOGITS
    éĺŁåĴĮ
    0.08
    ãģ¾ãģļ
    0.07
    -Za
    0.07
    lian
    0.07
    yak
    0.07
    SSION
    0.07
    mung
    0.07
    æµģéĢļèĤ¡
    0.07
    è´¹çĶ¨åĴĮ
    0.07
    iaan
    0.06
    Activations Density 0.156%

    No Known Activations