© 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. 43174
    Prev
    Next
    INDEX
    Explanations

    code blocks, assignments, and function calls

    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
    (""),
    -0.07
    .hasOwnProperty
    -0.07
    -
    -0.07
    .nodeType
    -0.07
    æĪijä»¬çŁ¥éģĵ
    -0.07
    èIJ¤çģ«
    -0.06
    =>
    -0.06
    ->
    -0.06
    çļĦéľĢè¦ģ
    -0.06
    çļĦç¼ĺæķħ
    -0.06
    POSITIVE LOGITS
    èī²åĪĹ
    0.08
    ìŀ¥ìĿĢ
    0.08
    esch
    0.08
    ìĿ´ëŀĢ
    0.08
    ì°¨ëĬĶ
    0.07
    åª
    0.07
    alu
    0.07
     $($
    0.07
    ìłĦìĿĢ
    0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.07
    Activations Density 0.029%

    No Known Activations