© 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. 62356
    Prev
    Next
    INDEX
    Explanations

    json package versions

    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
    otis
    -0.07
     gev
    -0.06
    ä½ij
    -0.06
    ä¸Ĭåĵģ
    -0.06
    ä»ħæѤ
    -0.06
    ä¸įåıij
    -0.06
    egner
    -0.06
    (typeof
    -0.06
    inne
    -0.06
    ä»ħä»ħæĺ¯
    -0.06
    POSITIVE LOGITS
    lice
    0.09
    ä¾ĿåŃĺ
    0.08
    ä¾Ŀèµĸ
    0.08
    ä¾Ŀèµĸäºİ
    0.07
    depend
    0.07
    uten
    0.07
    ASI
    0.07
    apers
    0.07
     depend
    0.07
    åĨį说
    0.07
    Activations Density 0.045%

    No Known Activations