© 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. 34898
    Prev
    Next
    INDEX
    Explanations

    fractional values and units

    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
    ensee
    -0.08
    γÏĩ
    -0.08
    (SE
    -0.08
    Ñıн
    -0.07
    ariales
    -0.07
    htmlspecialchars
    -0.07
    Äĥri
    -0.07
    aruhi
    -0.07
    enser
    -0.07
    rices
    -0.07
    POSITIVE LOGITS
     fractional
    0.08
     fraction
    0.08
    fraction
    0.07
    Fraction
    0.07
     fractions
    0.07
    çĻ¾åĪĨ
    0.06
     Fraction
    0.06
    éĩijä¸Ŀ
    0.06
    rap
    0.06
    åįłåħ¨åĽ½
    0.06
    Activations Density 0.005%

    No Known Activations