© 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. 43680
    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
    çIJ²
    -0.08
    æĪijçļĦ人
    -0.08
    beau
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    athe
    -0.07
    iale
    -0.07
    人已
    -0.07
    说åIJ§
    -0.07
    客çļĦ
    -0.07
    æĪij并ä¸į
    -0.07
    POSITIVE LOGITS
    æľīåħ³äºİ
    0.08
    çļĦæĺ¯
    0.07
    åĴĮçIJĨ解
    0.07
    話é¡Į
    0.06
    ä»Ĭå¹´
    0.06
    ÖĦ
    0.06
    åħ³äºİ
    0.06
    æľīåħ³
    0.06
    pects
    0.06
     instead
    0.06
    Activations Density 0.000%

    No Known Activations