© 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. 50367
    Prev
    Next
    INDEX
    Explanations

    xml/xaml/code syntax

    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
    åı¦å¤ĸä¸Ģ个
    -0.10
    åı¦å¤ĸä¸Ģç§į
    -0.10
    æŁ¥çľĭåħ¨æĸĩ
    -0.09
    oš
    -0.09
     Chiar
    -0.09
    .defaults
    -0.08
    ag
    -0.08
    dued
    -0.08
    еÑĢб
    -0.08
     Scu
    -0.08
    POSITIVE LOGITS
    ambi
    0.06
     pret
    0.06
    0.06
    ë¦ĩ
    0.06
    ä¸ī峡
    0.06
    ACH
    0.05
     Het
    0.05
    ä¸įåıĬ
    0.05
    eien
    0.05
     it
    0.05
    Activations Density 0.002%

    No Known Activations