© 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. 50840
    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
    æīĭæľºç«Ļ
    -0.08
    å°ĨæĿ¥çļĦ
    -0.07
    миÑĢа
    -0.07
    atera
    -0.07
    olid
    -0.07
    давно
    -0.07
    çĸİ
    -0.07
    baru
    -0.07
    emez
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    POSITIVE LOGITS
    erva
    0.08
    æľīçĶŁ
    0.07
    ())[
    0.06
     ëķĮê°Ģ
    0.06
     Ga
    0.06
    æľīåĬł
    0.06
    åĿĬ
    0.06
    _parallel
    0.06
     sup
    0.06
    ç§ij
    0.06
    Activations Density 0.000%

    No Known Activations