© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18731
    Prev
    Next
    INDEX
    Explanations

    superlatives

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æľīæķĪæıIJåįĩ
    -0.09
    ÙĬص
    -0.07
    _ARG
    -0.07
    urgia
    -0.07
    Interceptor
    -0.07
    åľ¨åħ¨çIJĥ
    -0.07
    Ñĥда
    -0.07
    ÑĪов
    -0.07
    èĢħä¹Ł
    -0.06
     ÙħÙĤØ·
    -0.06
    POSITIVE LOGITS
    iest
    0.09
     suivante
    0.08
     poorest
    0.08
     closest
    0.07
     ×ij×Ļ×ķתר
    0.07
     suivants
    0.07
     hottest
    0.07
     nearest
    0.07
    /latest
    0.07
     brightest
    0.07
    Activations Density 1.244%

    No Known Activations