© 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. 55423
    Prev
    Next
    INDEX
    Explanations

    large numbers or amounts

    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
    æľĢé«ĺçļĦ
    -0.08
     everybody
    -0.07
    ciel
    -0.07
    æĺķ
    -0.07
    åIJĮæĦıåIJİ
    -0.06
    æľĢæĹ©çļĦ
    -0.06
     Compat
    -0.06
    缴èĩ³
    -0.06
    å½·
    -0.06
    cala
    -0.06
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.14
    人æĪĸ
    0.12
    æĪĸèĢħæľī
    0.12
    æĬķèµĦæĪĸ
    0.11
    æĪĸå¤ļ
    0.11
    å¤įåĪ¶æĪĸ
    0.11
    åĽ¾çīĩæĪĸ
    0.11
    æĢ§æĪĸ
    0.10
    å·¥ä½ľæĪĸ
    0.10
    æĸĩ件æĪĸ
    0.10
    Activations Density 0.228%

    No Known Activations