© 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. 27311
    Prev
    Next
    INDEX
    Explanations

    $$ symbol and math variables

    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
    æĹłè®º
    -0.08
    ä¸įåĪĨ
    -0.07
    豪
    -0.06
    ynth
    -0.06
     regardless
    -0.06
    ä»»ä½ķ责任
    -0.06
     unspecified
    -0.06
    enth
    -0.06
    æĹłè®ºæĺ¯
    -0.06
    imm
    -0.06
    POSITIVE LOGITS
    å¿ħ须符åIJĪ
    0.14
    符åIJĪ
    0.13
    åºĶ符åIJĪ
    0.13
    ä¸¥æł¼éģµå®Ī
    0.13
    符åIJĪåĽ½å®¶
    0.12
    符åIJĪè¦ģæ±Ĥ
    0.12
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.12
    符åIJĪæĿ¡ä»¶
    0.11
    å¿ħé¡»æĺ¯
    0.11
    并确ä¿Ŀ
    0.11
    Activations Density 0.032%

    No Known Activations