© 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. 58747
    Prev
    Next
    INDEX
    Explanations

    programming and games

    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
    okes
    -0.09
    æĻ¨æĬ¥
    -0.08
    æĽ´åĬłåĬªåĬĽ
    -0.08
    باÙĥ
    -0.07
    vlc
    -0.07
    #region
    -0.07
    .asc
    -0.07
     chô
    -0.07
    मà¥į
    -0.07
    è¿ŀå¿ĥ
    -0.07
    POSITIVE LOGITS
    ights
    0.07
     platforms
    0.07
    å¾ģç¨ĭ
    0.06
    æī£
    0.06
    ר×Ļ×Ŀ
    0.06
    enet
    0.06
     Guardian
    0.06
     e
    0.06
     platform
    0.06
    ayed
    0.06
    Activations Density 0.004%

    No Known Activations