© 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. 37624
    Prev
    Next
    INDEX
    Explanations

    IDs and numbering

    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
    anja
    -0.08
    Ả
    -0.07
    ATUS
    -0.07
    è´°
    -0.07
    è¿Ľè¡Įä¸Ģ次
    -0.07
    èĸĦå¼±çݯèĬĤ
    -0.07
    agi
    -0.07
    -feed
    -0.07
    isFunction
    -0.07
    inions
    -0.07
    POSITIVE LOGITS
    ç¼ĸåı·
    0.19
    çķªåı·
    0.16
     numbering
    0.16
     numbered
    0.15
     номеÑĢа
    0.14
     identifiers
    0.14
    åı·çłģ
    0.14
     номеÑĢ
    0.14
     IDs
    0.13
    ç·¨èĻŁ
    0.13
    Activations Density 1.106%

    No Known Activations