© 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. 49640
    Prev
    Next
    INDEX
    Explanations

    neuroscience publications journal details

    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
    åħ¬æĬ¥
    -0.07
     வழ
    -0.06
    çŁ
    -0.06
    ativer
    -0.06
    èĩªå·±çļĦæĥħ绪
    -0.06
     longtemps
    -0.06
    à¸Īาร
    -0.06
     pip
    -0.06
    ä¸ĥåįģäºĮ
    -0.06
    رØŃ
    -0.06
    POSITIVE LOGITS
     inaugural
    0.09
     budding
    0.08
    γο
    0.07
    é¦ĸå±Ĭ
    0.07
    èĬ±ä¸Ģ
    0.07
    ehu
    0.07
    eti
    0.07
    hana
    0.07
    OffsetTable
    0.07
    ä»ĭçŁ³
    0.07
    Activations Density 0.027%

    No Known Activations