© 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. 15493
    Prev
    Next
    INDEX
    Explanations

    _rewriteComputeO

    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
    OrUpdate
    -0.08
    æ³½æ°ij
    -0.08
    endl
    -0.08
    è¦ģä¹Īæĺ¯
    -0.08
    è¦ģä¹Ī
    -0.08
    astr
    -0.08
    cott
    -0.08
    ì²´ìĿ¸
    -0.08
    ilst
    -0.07
    IfExists
    -0.07
    POSITIVE LOGITS
    ä½İéĢŁ
    0.06
    ä¸ĭåIJĮ
    0.06
     loi
    0.06
    建å®ī
    0.06
    æĬĬ
    0.06
    _rewrite
    0.06
    ä¸īä¸ĥ
    0.06
     Loi
    0.06
    amik
    0.06
    æĬµ
    0.06
    Activations Density 0.001%

    No Known Activations