© 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. 46315
    Prev
    Next
    INDEX
    Explanations

    discrete signals or transforms

    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
    æ¾Ī
    -0.08
    IES
    -0.08
    áĥ
    -0.07
    bies
    -0.07
    æĥ°
    -0.07
    scribe
    -0.07
    riel
    -0.07
    ãĥªãĤ¨
    -0.07
    \Input
    -0.07
    entrant
    -0.07
    POSITIVE LOGITS
     discrete
    0.15
     discre
    0.12
     discret
    0.11
    离æķ£
    0.10
    _PIXEL
    0.08
    åĥıç´ł
    0.08
    crete
    0.08
    æł¼åŃIJ
    0.08
    æł¼
    0.08
    /grid
    0.07
    Activations Density 0.067%

    No Known Activations