© 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. 4326
    Prev
    Next
    INDEX
    Explanations

    calculate, compute, count, winner

    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
    æĪij们认为
    -0.08
    osh
    -0.08
    CHED
    -0.08
    arcz
    -0.08
    å¼ĢèµĽ
    -0.08
    itam
    -0.08
     ['./
    -0.08
    GRE
    -0.07
    æµģåĭķ
    -0.07
    OSH
    -0.07
    POSITIVE LOGITS
    计ç®Ĺåĩº
    0.09
     compute
    0.08
    计ç®Ĺ
    0.08
     calculations
    0.08
    Compute
    0.08
     Compute
    0.08
    .compute
    0.08
    æ±Ĥåĩº
    0.07
     calculate
    0.07
     computed
    0.07
    Activations Density 0.024%

    No Known Activations