© 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. 59003
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and fractions

    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
    åıĪæĬĬ
    -0.07
    esser
    -0.07
    umed
    -0.06
    ÑįÑħ
    -0.06
    山谷
    -0.06
    memberof
    -0.06
    ä¾Ŀæīĺ
    -0.06
    ero
    -0.06
    esos
    -0.06
    enj
    -0.06
    POSITIVE LOGITS
    veux
    0.08
    循åºı
    0.08
    inds
    0.07
    çĪ±ä¸į
    0.07
    #=
    0.07
    ?=
    0.07
    ientos
    0.07
     ~=
    0.07
    åĽ¢åĽ¢
    0.07
    Coeff
    0.07
    Activations Density 0.008%

    No Known Activations