© 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. 55972
    Prev
    Next
    INDEX
    Explanations

    /bin/env followed by language

    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
    OperationException
    -0.07
    DAQ
    -0.07
    _if
    -0.07
    ¾
    -0.07
    åįĥæĸ¤
    -0.06
    opo
    -0.06
    IfNeeded
    -0.06
     detail
    -0.06
    \\/
    -0.06
    -sdk
    -0.06
    POSITIVE LOGITS
    æģ¶
    0.08
    è£ģåīª
    0.08
    è£ģ
    0.08
    欢åĸľ
    0.07
    пÑĢиÑıÑĤ
    0.07
    tg
    0.07
    ighting
    0.07
    ecie
    0.07
    æĥ¡
    0.07
    ç¥ŀä¹ĭ
    0.07
    Activations Density 0.217%

    No Known Activations