© 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. 31184
    Prev
    Next
    INDEX
    Explanations

    maximize efficiency

    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
    liness
    -0.09
    ¦
    -0.08
    mans
    -0.07
    umat
    -0.07
     Tatsache
    -0.07
    人æĿ¥è¯´
    -0.07
    IDO
    -0.07
    sweise
    -0.07
    sWith
    -0.07
    spath
    -0.07
    POSITIVE LOGITS
    /max
    0.13
    IMUM
    0.13
    /min
    0.10
    imize
    0.09
    imized
    0.09
     sayıda
    0.08
    åĴĮæľĢ
    0.08
    /close
    0.08
    наÑĩа
    0.08
     Hinblick
    0.07
    Activations Density 0.029%

    No Known Activations