© 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. 37901
    Prev
    Next
    INDEX
    Explanations

    finding solutions and understanding

    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
    ongyang
    -0.09
     pledges
    -0.08
    大åIJį
    -0.08
    atakan
    -0.08
    arshal
    -0.08
    ä¸įçIJĨæĥ³
    -0.08
    ä»İçİ°åľ¨å¼Ģå§ĭ
    -0.08
    天äºĨ
    -0.08
    è¿Ľä¸ĢæŃ¥å¢ŀ强
    -0.08
    eprom
    -0.08
    POSITIVE LOGITS
     knowledge
    0.08
    çŁ¥éģĵ
    0.08
     quickly
    0.08
    解é¢ĺ
    0.08
     understanding
    0.07
    æ´ŀå¯ŁåĬĽ
    0.07
    å¿«éĢŁ
    0.07
     γνÏİ
    0.07
     knowing
    0.07
     insight
    0.07
    Activations Density 0.028%

    No Known Activations