© 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. 58914
    Prev
    Next
    INDEX
    Explanations

    mathematical equations with variables

    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
    -0.08
    ighted
    -0.08
    ÑĮÑĪе
    -0.07
    àºŃàºĩ
    -0.07
    chet
    -0.07
    aceous
    -0.07
    ัà¸ĩ
    -0.07
    ect
    -0.07
    ahkan
    -0.07
    retty
    -0.06
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.10
    er
    0.08
    м
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    åIJĦç§įåIJĦæł·
    0.08
    ä¸įåı¯æĢĿè®®
    0.07
    й
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    åIJĦç§įåIJĦæł·çļĦ
    0.07
    èĢ³çĨŁèĥ½è¯¦
    0.07
    Activations Density 0.002%

    No Known Activations