© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37574
    Prev
    Next
    INDEX
    Explanations

    operators and definitions

    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
    Negative Logits
    lai
    -0.09
    önen
    -0.08
     bezieh
    -0.08
    preso
    -0.08
    yscale
    -0.08
    doÄŁan
    -0.08
    elper
    -0.08
    lott
    -0.08
    theValue
    -0.08
    åħ¬ç§¯
    -0.08
    POSITIVE LOGITS
    /=
    0.09
    ï¸ı
    0.08
    ir
    0.07
    /OR
    0.07
    æ¯Ľæ³½ä¸ľ
    0.06
    äºĨè¿ĩåİ»
    0.06
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.06
     (
    0.06
    ;
    0.06
    ãģ£ãģĵ
    0.06
    Activations Density 0.046%

    No Known Activations