© 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. 30875
    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
    aps
    -0.08
     maga
    -0.08
    ç»ı纪
    -0.08
    ç§ģæĪ¿
    -0.07
    ubin
    -0.07
    大åı¯
    -0.07
    æīģ
    -0.07
    alleries
    -0.07
    plib
    -0.07
    achen
    -0.07
    POSITIVE LOGITS
     Rae
    0.07
    åĩĢåĪ©æ¶¦ä¸º
    0.07
     Zahn
    0.07
    ä¸ĭ载使çĶ¨
    0.06
    mq
    0.06
    tk
    0.06
    _BATCH
    0.06
    æĪļ
    0.06
    หà¹Į
    0.06
    either
    0.06
    Activations Density 0.000%

    No Known Activations