© 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. 45962
    Prev
    Next
    INDEX
    Explanations

    symbol or greek letter followed by `_` or `(`

    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
    inu
    -0.07
    ubat
    -0.06
    ory
    -0.06
    éĢļ天
    -0.06
    åĩĨå¤ĩ好çļĦ
    -0.06
    Proceed
    -0.06
    Ñģловно
    -0.06
    astle
    -0.06
    prech
    -0.06
    -c
    -0.06
    POSITIVE LOGITS
    ¬ģ
    0.09
    ä¸İåħ¶ä»ĸ
    0.09
    æĭĽèģĺåįķä½į
    0.08
    两åı£
    0.08
    两次
    0.08
    PUR
    0.07
    èĪĩåħ¶ä»ĸ
    0.07
    ä¸Ģ次çļĦ
    0.07
    åĴĮæĿİ
    0.07
    åħ©æ¬¡
    0.07
    Activations Density 0.043%

    No Known Activations