© 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. 13036
    Prev
    Next
    INDEX
    Explanations

    month and its abbreviations

    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
    =https
    -0.08
    anee
    -0.07
    vene
    -0.07
    è¾Ī
    -0.07
    iom
    -0.07
    leo
    -0.07
    anean
    -0.07
    çĤ¹åIJį
    -0.07
    vron
    -0.07
    leck
    -0.07
    POSITIVE LOGITS
     subdivisions
    0.07
    digits
    0.07
     digits
    0.07
    Ru
    0.07
    èĭ¦
    0.06
    é·¹
    0.06
     abbreviated
    0.06
    Integer
    0.06
    zim
    0.06
    ToInt
    0.06
    Activations Density 0.095%

    No Known Activations