© 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. 1400
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and units

    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
    è¯Ħä»·ä½ĵç³»
    -0.07
    åı«å¥½
    -0.07
    emente
    -0.07
    eran
    -0.07
    ongen
    -0.06
    ึ
    -0.06
     Primo
    -0.06
    è¿Ī
    -0.06
    zcze
    -0.06
     enn
    -0.06
    POSITIVE LOGITS
    ouc
    0.09
    è¹Ī
    0.07
    ades
    0.07
    otton
    0.07
    utori
    0.07
    éĩĪ
    0.07
    åĬŁ
    0.07
    rej
    0.07
    æĻ¯
    0.07
    .module
    0.07
    Activations Density 0.006%

    No Known Activations