© 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. 32065
    Prev
    Next
    INDEX
    Explanations

    numbers in scientific notation

    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
    iores
    -0.08
    zeb
    -0.08
    IRCLE
    -0.08
    entimes
    -0.08
    nder
    -0.08
    stash
    -0.08
    ypes
    -0.08
    mann
    -0.07
    arians
    -0.07
    iphers
    -0.07
    POSITIVE LOGITS
    ettle
    0.08
    夫æĸ¯åŁº
    0.07
    alling
    0.07
    AGIC
    0.07
    Ahead
    0.07
    icile
    0.07
    ilo
    0.07
    Äĩi
    0.07
    uppy
    0.07
    .HE
    0.06
    Activations Density 0.003%

    No Known Activations