© 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. 26441
    Prev
    Next
    INDEX
    Explanations

    special characters and separators

    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
    ç§
    -0.07
    -back
    -0.07
     undue
    -0.06
    æŁIJä¸Ģ
    -0.06
    å§ĭ
    -0.06
     uncon
    -0.06
    æĻ¦
    -0.06
    agit
    -0.06
    bsp
    -0.06
     amongst
    -0.06
    POSITIVE LOGITS
    omic
    0.07
     sconos
    0.07
    çļĦåģļæ³ķ
    0.07
    دÙĪز
    0.07
    .appspot
    0.07
    subcategory
    0.07
    çļĦè¯Ŀ
    0.06
    enheim
    0.06
     duga
    0.06
    processable
    0.06
    Activations Density 0.007%

    No Known Activations