© 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. 59962
    Prev
    Next
    INDEX
    Explanations

    differential or fractional variables

    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
    æıIJé«ĺèĩªèº«
    -0.08
    gara
    -0.08
    elay
    -0.07
    janya
    -0.07
    rello
    -0.07
    æķ¦
    -0.07
    温åĵ¥åįİ
    -0.07
     konce
    -0.07
    羯
    -0.07
    åħ±åº¦
    -0.07
    POSITIVE LOGITS
    .au
    0.07
    å¹ħ度
    0.07
    åĨ³
    0.06
    缴åĪ°
    0.06
    åİĺ
    0.06
    (change
    0.06
     until
    0.06
    ingat
    0.06
    contest
    0.06
    oyal
    0.06
    Activations Density 0.002%

    No Known Activations