© 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. 13479
    Prev
    Next
    INDEX
    Explanations

    programming language 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
    ForEach
    -0.07
    _FOREACH
    -0.07
    æķ¬çķı
    -0.06
     distinguished
    -0.06
    ErrorHandler
    -0.06
    жней
    -0.06
    ä¸įéĢĤåºĶ
    -0.06
    forEach
    -0.06
    æĬĢæľ¯åĴ¨è¯¢
    -0.06
     —
    -0.06
    POSITIVE LOGITS
    ipu
    0.08
    -commit
    0.08
    .loadData
    0.08
    æĪIJç«ĭ
    0.08
    /values
    0.07
    bast
    0.07
    æݨç®Ĺ
    0.07
    åĴĮåįķä½į
    0.07
    AndView
    0.07
    commit
    0.07
    Activations Density 0.014%

    No Known Activations