© 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. 41699
    Prev
    Next
    INDEX
    Explanations

    first operand

    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
    è¿ĺåĸľæ¬¢
    -0.08
    <|repo_name|>
    -0.08
    ochen
    -0.08
    大æ¦Ĥçİĩ
    -0.07
    ãĥ£ãĥ³
    -0.07
    ificantly
    -0.07
    _prepare
    -0.07
    æľīå¿ĥ
    -0.07
    winkel
    -0.07
    _Status
    -0.07
    POSITIVE LOGITS
    就好åĥı
    0.10
    æĪĸèĢħ说
    0.09
    ä½ĵçİ°åľ¨
    0.08
    代表äºĨ
    0.08
    代表çļĦ
    0.08
    il
    0.07
     seolah
    0.07
    ilus
    0.07
    å°±åĥıæĺ¯
    0.07
    èįĴ
    0.07
    Activations Density 0.006%

    No Known Activations