© 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. 27235
    Prev
    Next
    INDEX
    Explanations

    types of industries

    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
     fisc
    -0.08
    <|box_end|>
    -0.08
    çļĦéĥ¨ä½į
    -0.07
    ikken
    -0.07
    upu
    -0.07
    çļĦ年代
    -0.07
    à¸ŀ
    -0.07
    æĸ¹éĿ¢ä¹Ł
    -0.07
    uket
    -0.07
    çļĦç§įç±»
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.09
    åĿĩæľī
    0.09
    åĨħçļĦ
    0.08
    èIJ½çļĦ
    0.08
    itzer
    0.07
    ä¼łæĿ¥çļĦ
    0.07
    åĴĮåįķä½į
    0.07
    ë³Ħ
    0.07
    çļĦæ°Ķ
    0.07
    å°¤åħ¶æĺ¯
    0.07
    Activations Density 0.008%

    No Known Activations