© 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. 15894
    Prev
    Next
    INDEX
    Explanations

    meaningful, insightful, profound themes

    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
    å®ŀåĬ¡
    -0.07
    unis
    -0.07
    åIJĦç§ij
    -0.07
    å®ŀæĥħ
    -0.07
     notorious
    -0.07
    è¾£
    -0.06
    çģ«åĬĽ
    -0.06
    Excel
    -0.06
     disag
    -0.06
     Excel
    -0.06
    POSITIVE LOGITS
    åįĩåįİ
    0.10
    åĨħ涵
    0.10
    æĸĩåĮĸåĨħ涵
    0.09
    æĽ´æ·±
    0.09
     meanings
    0.09
     significance
    0.09
    çļĦåĨħ涵
    0.09
    å±ĤéĿ¢ä¸Ĭ
    0.09
    å¯ĵ
    0.09
     loft
    0.09
    Activations Density 0.075%

    No Known Activations