© 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. 22632
    Prev
    Next
    INDEX
    Explanations

    percentage signs and calculation

    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
    ail
    -0.07
    utel
    -0.07
    ick
    -0.07
    è´«
    -0.06
    qs
    -0.06
    让æĪijä»¬åľ¨
    -0.06
     inherit
    -0.06
     –
    -0.06
     bis
    -0.06
    æĦ
    -0.06
    POSITIVE LOGITS
     calculates
    0.08
    raries
    0.08
    计ç®Ĺåĩº
    0.08
    imbau
    0.08
    اÙħÙĬØ©
    0.08
    计ç®Ĺ
    0.08
    åħ¨åĬĽåģļ好
    0.08
    ftware
    0.07
    PLIED
    0.07
    å¾Ĺæ°´
    0.07
    Activations Density 0.003%

    No Known Activations