© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17514
    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
    _compiler
    -0.08
    çĥĤ
    -0.08
     Cutter
    -0.07
    åŁ¹è®ŃåĴĮ
    -0.07
     Sunder
    -0.07
    ä¸Ģæł·çļĦ
    -0.07
     Dung
    -0.07
    åıĭæĥħéĵ¾æİ¥
    -0.07
    çĪĽ
    -0.07
     vess
    -0.07
    POSITIVE LOGITS
    å¦Ĥ约
    0.07
    é½Ĭ
    0.07
    iros
    0.07
    äºijå±±
    0.06
    <|im_start|>
    0.06
    èģ²æĺİ
    0.06
    apon
    0.06
    æ£
    0.06
     seize
    0.06
    æĬ¥éĢģ
    0.06
    Activations Density 0.000%

    No Known Activations