© 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. 13626
    Prev
    Next
    INDEX
    Explanations

    equatorial, pre, ajax, easing, Minsk

    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
     ("\
    -0.07
     Malam
    -0.06
     ($(
    -0.06
    borgen
    -0.06
    ?[
    -0.06
     ("
    -0.06
    çķĻä¸ĭæĿ¥çļĦ
    -0.06
     Bison
    -0.06
    ลà¹Īะ
    -0.06
    KNOWN
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
    ian
    0.07
    readcr
    0.07
    agul
    0.07
    é¸
    0.07
    è·¯éĢı
    0.07
    å¤įåħ´
    0.07
    CEL
    0.07
    ä¸īæĽ´
    0.07
     KERNEL
    0.07
    Activations Density 0.027%

    No Known Activations