© 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. 44576
    Prev
    Next
    INDEX
    Explanations

    jupit, jekyll, jupyter, jigsaw

    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
     jasa
    -0.09
    jÅ¡ÃŃ
    -0.09
    bject
    -0.09
    å¯ĤéĿĻ
    -0.08
    å¢ĥçķĮ
    -0.08
     жилÑĮÑı
    -0.08
    åħ¼å¤ĩ
    -0.08
    举æŃ¢
    -0.08
     Jewish
    -0.08
     Judaism
    -0.08
    POSITIVE LOGITS
    igsaw
    0.18
    ekyll
    0.18
    uxtap
    0.18
    upiter
    0.16
    OURNAL
    0.16
    upyter
    0.15
    enkins
    0.15
    acobian
    0.14
    aspers
    0.13
    ournals
    0.13
    Activations Density 0.979%

    No Known Activations