© 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. 49160
    Prev
    Next
    INDEX
    Explanations

    java, kotlin, or other programming libraries

    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
    å¾Ĺ天
    -0.08
    ove
    -0.08
    WithString
    -0.07
    è¿Ļç§įçĸ¾çĹħ
    -0.07
    *sizeof
    -0.07
    ool
    -0.07
    edImage
    -0.06
    ég
    -0.06
    stein
    -0.06
    ç»·
    -0.06
    POSITIVE LOGITS
    ToArray
    0.06
    é¦ĸè¦ģ
    0.06
    EOS
    0.06
    ียà¸Ķ
    0.06
    ÏģÏħθ
    0.06
    æľįåĬ¡ä¸ļ
    0.06
    NIS
    0.06
    atia
    0.06
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    0.06
    /false
    0.06
    Activations Density 0.126%

    No Known Activations