© 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. 25887
    Prev
    Next
    INDEX
    Explanations

    rounding to the nearest million

    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
    è¾ħ
    -0.08
    ID
    -0.07
    æ¯ķç«Łæĺ¯
    -0.07
    neys
    -0.07
    noi
    -0.06
    è¾ħåĬ©
    -0.06
    æ¯ķç«Ł
    -0.06
    éĥ¨åĪĨ
    -0.06
    inet
    -0.06
    outu
    -0.06
    POSITIVE LOGITS
    каÑģ
    0.09
    sce
    0.08
    isto
    0.07
    å¤ļåģļ
    0.07
     multiples
    0.07
    èµĦ产交æĺĵ
    0.07
    omber
    0.07
    åħ¶äºº
    0.07
    itor
    0.07
    zes
    0.07
    Activations Density 0.005%

    No Known Activations