© 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. 32346
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    (LED
    -0.10
    pira
    -0.10
    产åĵģä¸Ńå¿ĥ
    -0.09
    elpers
    -0.09
    å°Ķå¤ļ
    -0.09
    SingleNode
    -0.09
    ÅĽcie
    -0.09
    ãģ£ãģ·
    -0.09
    æľī家
    -0.09
     niên
    -0.09
    POSITIVE LOGITS
    -like
    0.11
    çļĦæľ¬è´¨
    0.07
    å°±æĺ¯ä¸Ģç§į
    0.07
    /
    0.06
    æĦıä¹īä¸ĬçļĦ
    0.06
    éĤ£æł·çļĦ
    0.06
    orous
    0.06
    -type
    0.06
    X
    0.06
    éĽıå½¢
    0.06
    Activations Density 0.149%

    No Known Activations