© 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. 30341
    Prev
    Next
    INDEX
    Explanations

    chlorohydrin

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ément
    -0.06
    ä¸įæ²»
    -0.06
    æIJ
    -0.06
    æ¯ıä¸Ģ
    -0.06
    åŃ°
    -0.06
    ToJson
    -0.06
    ?v
    -0.05
    æĸ°åĬłåĿ¡
    -0.05
    Ñİ
    -0.05
    첫
    -0.05
    POSITIVE LOGITS
    asilan
    0.09
    er
    0.09
    éĤĢæĤ¨
    0.08
     ÙħئÙĪÙĬØ©
    0.08
    erior
    0.08
    oce
    0.08
    uwen
    0.08
    æĬķ稿éĤ®ç®±
    0.08
     недел
    0.08
    ater
    0.08
    Activations Density 0.065%

    No Known Activations