© 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. 40675
    Prev
    Next
    INDEX
    Explanations

    questions and tells

    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
    èĭ±åĭĩ
    -0.08
    ä¾ĭ
    -0.08
    olt
    -0.07
    serter
    -0.07
    STYPE
    -0.07
    ERO
    -0.07
    olian
    -0.07
    鼶
    -0.07
    _ASSUME
    -0.07
    ohl
    -0.07
    POSITIVE LOGITS
    å·¥ä½ľéĩįçĤ¹
    0.08
    æľīä»Ģä¹Īä¸įåIJĮ
    0.08
    èĩªå·±çļĦå·¥ä½ľ
    0.08
    ä½łè®¤ä¸º
    0.07
    纾
    0.07
     inspiration
    0.07
    说å®ŀè¯Ŀ
    0.07
    ä¸İæľ¬ç«Ļ
    0.07
     Tell
    0.07
    æĤ¨å½ĵåīįçļĦ
    0.07
    Activations Density 0.341%

    No Known Activations