© 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. 39213
    Prev
    Next
    INDEX
    Explanations

    complacency, victory lap, lane, moments, pressure, fame

    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
    .googleapis
    -0.08
    æĹłåı¯å¥Īä½ķ
    -0.07
    å·¢
    -0.07
    çļĦæīĭå·¥
    -0.07
    éĩij森
    -0.07
    åıªè¦ģ
    -0.07
     salvage
    -0.07
    _MISSING
    -0.07
    xon
    -0.07
    没æľīåĬŀæ³ķ
    -0.07
    POSITIVE LOGITS
    éĶ¦ä¸Ĭæ·»èĬ±
    0.09
    éªĦ
    0.08
    èѦæĥķ
    0.08
    å§ĭç»Īä¿ĿæĮģ
    0.08
    æıIJéĨĴèĩªå·±
    0.08
    å¯Įè´µ
    0.08
     humility
    0.08
    è¬Ļ
    0.08
    éĢĨå¢ĥ
    0.08
    è°¦èĻļ
    0.08
    Activations Density 0.031%

    No Known Activations