© 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. 20885
    Prev
    Next
    INDEX
    Explanations

    template or configuration settings

    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®Ĺ主
    -0.07
    ä¸ĢçĤ¹çļĦ
    -0.07
    ä¸ĢæĹģçļĦ
    -0.07
    åIJ¦
    -0.07
    çīĪçļĦ
    -0.06
    chol
    -0.06
     Edition
    -0.06
    >Title
    -0.06
    æĹłä¸į
    -0.06
    æ»ĵ
    -0.06
    POSITIVE LOGITS
    ä¹Łæĺ¯è¿Ļæł·
    0.08
    åħ±åĪĨ
    0.07
    ืà¹Īà¸Ļ
    0.07
    æľīæķĪæľŁèĩª
    0.07
    å°Ĩæł¹æį®
    0.07
    .SOCK
    0.07
    elon
    0.06
    è¿Ļç§įä¸ľè¥¿
    0.06
    adang
    0.06
     konusunda
    0.06
    Activations Density 0.408%

    No Known Activations