© 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. 56721
    Prev
    Next
    INDEX
    Explanations

    chemical and biochemical signals

    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
    è¿Ļ两款
    -0.07
    ãģ¡ãģ¯
    -0.07
    ÑıÑĤа
    -0.07
    æµģæ´¾
    -0.06
    à¸ļัà¸ĩ
    -0.06
     positives
    -0.06
    fen
    -0.06
    濯
    -0.06
    yth
    -0.06
     ech
    -0.06
    POSITIVE LOGITS
    æ´»
    0.08
    _substr
    0.07
    .dylib
    0.07
     замоÑĢо
    0.07
    éĢ¸
    0.07
    çī©è´¨
    0.07
     subscript
    0.07
    aggio
    0.07
     мо
    0.07
     gz
    0.07
    Activations Density 0.001%

    No Known Activations