© 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. 64662
    Prev
    Next
    INDEX
    Explanations

    parse and register code

    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
    onet
    -0.08
    anzo
    -0.08
    ÏĦÎŃÏģ
    -0.08
    inken
    -0.08
    ngr
    -0.08
     ";
    -0.08
    üst
    -0.08
    oku
    -0.08
    ETYPE
    -0.07
    itom
    -0.07
    POSITIVE LOGITS
    ç½ķ
    0.06
    ·
    0.06
     cint
    0.06
    á½
    0.06
    æĸ¼
    0.06
    ftware
    0.06
     *
    0.06
    <
    0.05
    åĿĬ
    0.05
    èĢħçļĦ
    0.05
    Activations Density 0.067%

    No Known Activations