© 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. 65268
    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
    icin
    -0.07
    имо
    -0.07
    ä¸ĢèĪ¬çļĦ
    -0.07
    æĴ
    -0.06
    åĵŁ
    -0.06
    åħ¶ä¸Ĭ
    -0.06
    ajas
    -0.06
     inf
    -0.06
     Inv
    -0.06
    offre
    -0.06
    POSITIVE LOGITS
     ØŃدا
    0.08
    åıĬ家éķ¿
    0.08
    æħĭ
    0.08
     nextPage
    0.07
     mát
    0.07
     cá»ij
    0.07
    åı¥è¯Ŀ
    0.07
    _BGR
    0.07
    æīĶåĪ°
    0.07
    idon
    0.07
    Activations Density 0.000%

    No Known Activations