© 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. 27279
    Prev
    Next
    INDEX
    Explanations

    know before

    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
    ãĥªãĥ¥ãĥ¼
    -0.08
     excer
    -0.08
    边走
    -0.08
    ercul
    -0.08
    è·»
    -0.07
    usercontent
    -0.07
     Wilkinson
    -0.07
    ($(
    -0.07
    ãĤ¦ãĥī
    -0.07
    otov
    -0.07
    POSITIVE LOGITS
    ä¸Ģ天
    0.07
    arily
    0.07
    A
    0.07
    为äºĨ解åĨ³
    0.06
    chy
    0.06
    UTE
    0.06
    ETTA
    0.06
    FFFF
    0.06
    ä¸Ģ次
    0.06
    ål
    0.06
    Activations Density 0.001%

    No Known Activations