© 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. 3951
    Prev
    Next
    INDEX
    Explanations

    karma and karma yoga

    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
    otify
    -0.08
    EAU
    -0.08
    ivor
    -0.08
     brus
    -0.08
    ारà¥į
    -0.08
     cúp
    -0.08
    aille
    -0.07
     TUY
    -0.07
    家æĿij
    -0.07
    ä¹ĭæĢ¥
    -0.07
    POSITIVE LOGITS
    累累
    0.10
    åĸĦæģ¶
    0.10
     karma
    0.09
    积累çļĦ
    0.08
    éĢłçļĦ
    0.08
    æĹłéĩı
    0.08
    积累
    0.08
    alfa
    0.08
    æµģ转
    0.08
    ä»ĬçĶŁ
    0.08
    Activations Density 0.009%

    No Known Activations