© 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. 9632
    Prev
    Next
    INDEX
    Explanations

    transformations and operations on matrices

    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
    çī©æĸĻçļĦ
    -0.08
    Ñģел
    -0.08
    ä¹ĭçªĹ
    -0.08
    voz
    -0.07
    ردة
    -0.07
    è¿Ļ个éģĵçIJĨ
    -0.07
    uket
    -0.07
    à¸ĭà¹īà¸Ńà¸Ļ
    -0.07
    åľ¨å¿ħ
    -0.07
    éĺ»åĩ»æĪĺ
    -0.07
    POSITIVE LOGITS
    è¿ĩç¨ĭä¸Ń
    0.08
    åħĭæĸ¯
    0.08
     transformations
    0.08
     transform
    0.07
    éĻį
    0.07
     Transform
    0.07
    秩
    0.07
    _transform
    0.07
     transforms
    0.07
    çļĦè¿ĩç¨ĭä¸Ń
    0.07
    Activations Density 0.003%

    No Known Activations