© 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. 37589
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with subscripts

    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
    -0.20
    Ø©
    -0.18
    ness
    -0.14
    ighbors
    -0.10
    ryption
    -0.10
    entication
    -0.09
    age
    -0.09
    ÑİÑĤ
    -0.09
    à¸Ĥà¸Ńà¸ĩ
    -0.09
    apsed
    -0.09
    POSITIVE LOGITS
    ly
    0.17
    raries
    0.15
    ëį°
    0.11
    .mybatisplus
    0.11
    俱ä¹IJéĥ¨
    0.11
    enticate
    0.11
    缸è¾ħ缸æĪIJ
    0.11
    ãĤĪãģĨãģª
    0.11
    åħ¨å¿ĥåħ¨æĦı
    0.10
    ãĥ³
    0.10
    Activations Density 0.074%

    No Known Activations