© 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. 4700
    Prev
    Next
    INDEX
    Explanations

    chromatography, test, without

    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
     jinak
    -0.06
    io
    -0.06
    çĴĭ
    -0.06
     Terd
    -0.06
    çŃīäºĨ
    -0.06
    inery
    -0.06
    éĢĤé¾Ħ
    -0.06
     impossÃŃvel
    -0.06
    ôr
    -0.06
    enko
    -0.06
    POSITIVE LOGITS
     without
    0.20
    without
    0.20
     WITHOUT
    0.19
     بدÙĪÙĨ
    0.18
     Without
    0.18
    Without
    0.18
    _without
    0.18
     без
    0.17
     ohne
    0.17
     tanpa
    0.17
    Activations Density 1.017%

    No Known Activations