© 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. 47554
    Prev
    Next
    INDEX
    Explanations

    code, math, or programming keywords

    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
     ([[
    -0.11
    arra
    -0.09
     (((
    -0.07
    {:
    -0.07
    asher
    -0.07
    ((((
    -0.07
     Näh
    -0.07
    ([(
    -0.07
    _multiply
    -0.07
    amkan
    -0.07
    POSITIVE LOGITS
    ä¸į大äºİ
    0.08
    ä¸įå°ıäºİ
    0.07
    Ãłng
    0.07
     mesti
    0.07
    ä¸įè¦ģ太
    0.06
    ä¸įè¶ħè¿ĩ
    0.06
     !**
    0.06
    梧
    0.06
    issing
    0.06
    èĥ¤
    0.06
    Activations Density 0.003%

    No Known Activations