© 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. 7111
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with punctuation

    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
    å¾ĢæľŁåĽŀ顾
    -0.09
    uctor
    -0.09
    lei
    -0.09
    èĭ¥éĿŀ
    -0.08
    edar
    -0.08
    ETERS
    -0.08
    DEST
    -0.08
    hende
    -0.08
    åħ¨å·ŀ
    -0.08
    .Expect
    -0.08
    POSITIVE LOGITS
     DVR
    0.06
    æľŁ
    0.06
    æĦģ
    0.06
     infinity
    0.06
     Cl
    0.06
     C
    0.06
    åĸĭ
    0.05
     e
    0.05
    åľ°
    0.05
     D
    0.05
    Activations Density 0.001%

    No Known Activations