© 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. 11085
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    åį§é¾Ļ
    -0.07
    (which
    -0.06
    মà§ĩ
    -0.06
    èIJ¤çģ«
    -0.06
    æ§Ľ
    -0.06
     Hal
    -0.06
    é¸ŃèĽĭ
    -0.06
    äºijé¾Ļ
    -0.06
    تØŃ
    -0.06
    akedown
    -0.06
    POSITIVE LOGITS
    nap
    0.07
    паÑĤ
    0.07
     Suom
    0.07
    ampf
    0.07
    çĽ
    0.07
    ÙĨدگاÙĨ
    0.07
    اÙĤ
    0.07
     seiz
    0.07
    itech
    0.07
    ì¡´
    0.07
    Activations Density 0.018%

    No Known Activations