© 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. 38515
    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
    onia
    -0.08
    馴
    -0.08
    anh
    -0.07
    çķĻä¸ĭæĿ¥çļĦ
    -0.07
    æĪIJç«ĭæĹ¥æľŁ
    -0.07
     Belmont
    -0.07
    onio
    -0.07
    ång
    -0.06
    ä¸Ĭ马
    -0.06
    éĻĽ
    -0.06
    POSITIVE LOGITS
    essin
    0.08
    å¯ĵ
    0.07
    æĥľ
    0.07
    çĶ·å¥³ä¸įéĻIJ
    0.07
    ´
    0.06
    ä¸įç¦ģ
    0.06
    estra
    0.06
    æĢĶ
    0.06
    纯çĶµ
    0.06
    ustral
    0.06
    Activations Density 0.000%

    No Known Activations