© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42482
    Prev
    Next
    INDEX
    Explanations

    cells incubated with substances

    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
    lse
    -0.07
    .Decode
    -0.07
     иÑģко
    -0.06
    ุà¸Ļ
    -0.06
    ql
    -0.06
    é¢ĸ
    -0.06
    åĪĬåıij
    -0.06
    ugend
    -0.06
     BitSet
    -0.06
    spd
    -0.06
    POSITIVE LOGITS
     entweder
    0.09
    æµĵ度为
    0.09
     cultures
    0.08
    Culture
    0.08
    æŶéĹ´æĿ¥
    0.08
     culture
    0.08
    either
    0.08
     Culture
    0.08
     concentrations
    0.08
     either
    0.08
    Activations Density 0.715%

    No Known Activations