© 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. 57487
    Prev
    Next
    INDEX
    Explanations

    directory paths and locations

    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°±
    -0.07
     redraw
    -0.07
     berb
    -0.07
    bola
    -0.07
    æİī
    -0.06
    ä»Ĺ
    -0.06
    表ä¸Ń
    -0.06
     combination
    -0.06
     ëģĬ
    -0.06
    mier
    -0.06
    POSITIVE LOGITS
    åŃĺæĶ¾
    0.12
    æĸĩ件夹
    0.11
     files
    0.11
    è·¯å¾Ħ
    0.11
     folder
    0.10
     folders
    0.10
     directory
    0.10
    _files
    0.10
     PATH
    0.10
    Files
    0.09
    Activations Density 0.658%

    No Known Activations