© 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. 33358
    Prev
    Next
    INDEX
    Explanations

    determine the effect of

    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
    हà¥ģ
    -0.08
    zep
    -0.08
    riad
    -0.07
    utip
    -0.07
    ÑģÑĤей
    -0.07
    ä¼ģä¸ļè¦ģ
    -0.07
    åİļçĶŁ
    -0.07
    _il
    -0.07
    ÑĢÑĥжи
    -0.07
     zeker
    -0.07
    POSITIVE LOGITS
    æĺ¯åIJ¦åŃĺåľ¨
    0.10
    æĺ¯åIJ¦ä¼ļ
    0.09
    æĺ¯åIJ¦ä¸İ
    0.09
    æĺ¯åIJ¦
    0.09
    æĺ¯åIJ¦åľ¨
    0.09
    æĺ¯åIJ¦åħ·æľī
    0.08
    ä¸įåIJĮæŶ
    0.08
    æĺ¯åIJ¦èĥ½
    0.08
    /if
    0.08
     extent
    0.08
    Activations Density 0.742%

    No Known Activations