© 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. 43882
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. Nos

    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
    emm
    -0.08
    osas
    -0.07
    æĹłæĤĶ
    -0.07
    身价
    -0.07
    æµ´
    -0.07
     recip
    -0.07
    çļĦåįķä½į
    -0.07
    ¤íĮ
    -0.07
    çİ°å½¹
    -0.06
    $temp
    -0.06
    POSITIVE LOGITS
     Lowe
    0.09
    鸳
    0.08
    riel
    0.07
    _characters
    0.07
    «
    0.07
    æĴķ
    0.07
    eller
    0.07
    Characters
    0.07
    _linux
    0.07
    .getDefault
    0.07
    Activations Density 0.006%

    No Known Activations