© 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. 29662
    Prev
    Next
    INDEX
    Explanations

    calculation, calculation, calculation

    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
    خاص
    -0.07
    apos
    -0.07
    ArrayOf
    -0.07
     tả
    -0.07
    è¿Ļç§įä¸ľè¥¿
    -0.07
    æĺ¯ä»Ģä¹Īæł·çļĦ
    -0.06
    udel
    -0.06
    éĤ®ç¼ĸ
    -0.06
    orsch
    -0.06
     Observable
    -0.06
    POSITIVE LOGITS
     calculation
    0.16
     calculations
    0.16
     calculating
    0.15
     calculate
    0.15
    计ç®Ĺ
    0.15
    计ç®ĹçļĦ
    0.14
    计ç®Ĺåħ¬å¼ı
    0.14
    计ç®Ĺåĩº
    0.14
    计ç®Ĺæĸ¹æ³ķ
    0.14
     Calculation
    0.13
    Activations Density 0.024%

    No Known Activations