© 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. 48256
    Prev
    Next
    INDEX
    Explanations

    composition of various substances

    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
    ottage
    -0.07
    erma
    -0.07
    åį¿
    -0.07
    enberg
    -0.07
     que
    -0.07
    виÑĩ
    -0.07
     à¹Ĩ
    -0.07
    ãģĹãģıãģ¯
    -0.07
    ÑģÑĤен
    -0.06
    åºĩ
    -0.06
    POSITIVE LOGITS
     composition
    0.12
    composition
    0.11
     ÑģоÑģÑĤава
    0.11
     Composition
    0.11
    æĪIJåĪĨ
    0.10
     compositions
    0.10
    Composition
    0.10
    æĪIJåĪĨçļĦ
    0.10
    ç»ĦæĪIJçļĦ
    0.09
    ç»ĦæĪIJ
    0.09
    Activations Density 0.062%

    No Known Activations