© 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. 35076
    Prev
    Next
    INDEX
    Explanations

    variable differentiation wrt

    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
    abb
    -0.07
     elong
    -0.07
    avia
    -0.07
    åħŃåIJĪ
    -0.06
     allot
    -0.06
    æģIJ
    -0.06
    ä¸ĢåĪĨéĴŁ
    -0.06
    ossi
    -0.06
     bypass
    -0.06
     align
    -0.06
    POSITIVE LOGITS
     variables
    0.08
    variables
    0.07
    chooser
    0.07
     ξε
    0.07
    线ä¸ĬçļĦ
    0.07
    -lat
    0.07
    åıĺéĩı
    0.07
    _variables
    0.07
     Lat
    0.07
    /xml
    0.07
    Activations Density 0.012%

    No Known Activations