© 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. 37457
    Prev
    Next
    INDEX
    Explanations

    third derivative and cube root

    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
    ä¸¤å¼ł
    -0.10
    åIJijæĹ¥
    -0.08
    ouston
    -0.08
    寬
    -0.08
    å¼µ
    -0.08
    åıĮåŃIJ
    -0.07
     Breit
    -0.07
    oub
    -0.07
    çĭ©
    -0.07
     fed
    -0.07
    POSITIVE LOGITS
     cube
    0.14
    ç«ĭæĸ¹
    0.13
    cube
    0.13
     volumes
    0.12
     cubic
    0.12
     volume
    0.12
    ä½ĵ积
    0.12
     cubes
    0.12
    Cube
    0.11
    ç«ĭæĸ¹ç±³
    0.11
    Activations Density 0.059%

    No Known Activations