© 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. 47430
    Prev
    Next
    INDEX
    Explanations

    sourcing external connections

    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
    Einst
    -0.08
    eltas
    -0.08
    èµ°äºĨè¿ĩæĿ¥
    -0.07
    åħ±æ²»
    -0.07
     اÙĦإدارÙĬØ©
    -0.07
     CDU
    -0.07
    ypy
    -0.07
    æľīè¯Ŀ
    -0.07
    é¡¹çĽ®æī¿åĬŀåįķä½į
    -0.06
    ½Ķ
    -0.06
    POSITIVE LOGITS
    å¤ĸéĥ¨
    0.12
     external
    0.11
    çļĦå¤ĸéĥ¨
    0.11
     sourcing
    0.11
    sources
    0.11
     sources
    0.10
    å¤ĸçķĮçļĦ
    0.10
    External
    0.10
    æĿ¥æºIJ
    0.10
    external
    0.10
    Activations Density 0.641%

    No Known Activations