© 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. 35021
    Prev
    Next
    INDEX
    Explanations

    math operators like mod

    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
    ation
    -0.12
    ipse
    -0.09
    ly
    -0.09
    itous
    -0.08
    Ø©
    -0.08
    Ñģловно
    -0.08
    ãģ¦
    -0.08
    ение
    -0.08
    ously
    -0.08
    ettes
    -0.08
    POSITIVE LOGITS
    æĶ¾çŁ¢
    0.09
    çĦ¶æĺ¯
    0.09
    s
    0.09
    à¸Ĭาà¸ķิ
    0.09
    sing
    0.09
    er
    0.08
    ings
    0.08
    ÙħاÙĨ
    0.08
    itional
    0.07
    iw
    0.07
    Activations Density 0.007%

    No Known Activations