© 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. 23733
    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
    yens
    -0.09
    adah
    -0.08
    Listeners
    -0.07
    ezd
    -0.07
    GEST
    -0.07
    è¦ģä½ł
    -0.07
    æĻ¨æĬ¥
    -0.07
    åĮĹé£İ
    -0.07
    sert
    -0.07
    erts
    -0.07
    POSITIVE LOGITS
    纵
    0.06
    ita
    0.06
    doch
    0.06
    æĩ
    0.06
    landen
    0.06
    mot
    0.06
    è¸ı
    0.06
    åľ¨ä¸ĭéĿ¢
    0.06
    "#
    0.06
    _PLACE
    0.06
    Activations Density 0.000%

    No Known Activations