© 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. 26095
    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
    alang
    -0.06
    ç¡®å®ļ
    -0.06
    ç§ij
    -0.06
    æł¼
    -0.06
     hab
    -0.06
    åİĭ
    -0.06
    åĮħ
    -0.06
    åIJĮå·¥
    -0.06
    iris
    -0.06
    ä¹°
    -0.06
    POSITIVE LOGITS
    ngo
    0.08
    .fm
    0.08
    eor
    0.08
    ;/*
    0.08
    õi
    0.08
    ystate
    0.08
    åģ¥åĦ¿
    0.08
    ovah
    0.08
    trup
    0.07
    _srv
    0.07
    Activations Density 0.000%

    No Known Activations