© 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. 61510
    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
    ä¸ĭåIJĮ
    -0.08
    vos
    -0.07
    wijk
    -0.07
    гол
    -0.07
    æĶ¶æķĽ
    -0.07
    monic
    -0.07
     Besar
    -0.07
    éļ·
    -0.07
    æīŃ转
    -0.06
    åįķä½ĵ
    -0.06
    POSITIVE LOGITS
    æĪĺæ³ķ
    0.07
    .accept
    0.07
    sofar
    0.07
    жда
    0.07
    ãģ»ãģĨ
    0.06
    åį°è±¡
    0.06
    SPA
    0.06
    ä½ľåģĩ
    0.06
    æĺ¥åħī
    0.06
    ÙĨاس
    0.06
    Activations Density 0.000%

    No Known Activations