© 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. 40513
    Prev
    Next
    INDEX
    Explanations

    code, lisp, math, programming constructs

    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
    isd
    -0.07
    Ok
    -0.06
    FS
    -0.06
    ETTI
    -0.06
    rial
    -0.06
    ãĤĤãģ¡ãĤįãĤĵ
    -0.06
    lish
    -0.06
    æıIJ
    -0.06
     Ok
    -0.06
    prs
    -0.06
    POSITIVE LOGITS
    æĬĬä¸Ģ个
    0.09
    å°Ĩä¸Ģ个
    0.09
     suatu
    0.08
    _generic
    0.08
    orio
    0.08
    åľ¨æŁIJ
    0.08
    _orient
    0.08
    æŁIJä¸Ģ天
    0.08
    æľ¬çīĪ
    0.08
    çļĦ人æĿ¥è¯´
    0.08
    Activations Density 0.004%

    No Known Activations