© 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. 13637
    Prev
    Next
    INDEX
    Explanations

    funded by, provided by, developed by

    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
    ä¸Ģä¾ĭ
    -0.07
    è¿Ļ款产åĵģ
    -0.07
    æĥħç»ĵ
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    çļĦä¸Ģçݯ
    -0.07
     suatu
    -0.07
    çļĦä¸Ģ件äºĭ
    -0.07
    pedia
    -0.06
    dad
    -0.06
    ä¸Ģ件äºĭ
    -0.06
    POSITIVE LOGITS
    żej
    0.07
     غاÙĬØ©
    0.07
    oyer
    0.07
    çĦ¶æĺ¯
    0.06
    åįĩåĪĿ
    0.06
    åı«åģļ
    0.06
    ãģ¿ãģ«
    0.06
    arqu
    0.06
    idaya
    0.06
     réellement
    0.06
    Activations Density 1.136%

    No Known Activations