© 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. 58020
    Prev
    Next
    INDEX
    Explanations

    computational and scientific terms

    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
    ANCELED
    -0.09
    ictured
    -0.07
    entimes
    -0.07
    anzi
    -0.07
     unik
    -0.07
    æĺ¥åįİ
    -0.07
    æĽ¾ç»ıçļĦ
    -0.07
     salat
    -0.07
     nonprofit
    -0.07
    oulos
    -0.07
    POSITIVE LOGITS
     upto
    0.12
     Pune
    0.12
     âĤ¹
    0.12
     Delhi
    0.11
     Bhar
    0.11
     lakh
    0.11
    åį°åº¦
    0.11
     Punjab
    0.11
    India
    0.11
     India
    0.11
    Activations Density 0.103%

    No Known Activations