© 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. 39118
    Prev
    Next
    INDEX
    Explanations

    compression and zip files

    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
    æĸĵ
    -0.10
    çĮªèĤĿ
    -0.07
    xFFFFFF
    -0.07
    kez
    -0.07
    åĩĨ
    -0.07
    inic
    -0.07
    imson
    -0.07
    venues
    -0.07
    swick
    -0.07
    ä¸Ģ读
    -0.07
    POSITIVE LOGITS
    åİĭ缩
    0.14
     compression
    0.14
    .compress
    0.13
    Compression
    0.12
     compress
    0.12
     Compression
    0.12
    compression
    0.12
     compressed
    0.11
     gzip
    0.11
    compress
    0.11
    Activations Density 0.179%

    No Known Activations