© 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. 18581
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    gnore
    -0.11
     ìĿ¸íķ´
    -0.07
    ippets
    -0.07
    лиÑĩно
    -0.07
    à¥įà¤ŀ
    -0.07
    asar
    -0.07
    reatest
    -0.07
    _DYNAMIC
    -0.06
    oyo
    -0.06
    ly
    -0.06
    POSITIVE LOGITS
    achim
    0.09
    artes
    0.08
    åĭĻ
    0.08
    注æĦıçļĦæĺ¯
    0.07
    uschen
    0.07
    ×ľ×ª
    0.07
    ÐĸÐĶ
    0.07
    jenigen
    0.07
    upan
    0.07
    ÙĪÙħÙĬØ©
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.