© 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. 4004
    Prev
    Next
    INDEX
    Explanations

    mathematical variable followed by exponent

    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
    byt
    -0.08
     spar
    -0.07
    립
    -0.07
    èĦĬ
    -0.07
    Persistent
    -0.07
    زاÙħ
    -0.07
    å¯Ĩä¸įåı¯åĪĨ
    -0.06
     Overse
    -0.06
    زر
    -0.06
    CDATA
    -0.06
    POSITIVE LOGITS
    ÐŁÐĺ
    0.07
    åĬłä¸Ĭ
    0.07
     exped
    0.07
    éĹª
    0.07
     plus
    0.06
    боÑĢÑĭ
    0.06
    å±Ĥ
    0.06
    unki
    0.06
    ytt
    0.06
    ahr
    0.06
    Activations Density 0.057%

    No Known Activations