© 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. 43208
    Prev
    Next
    INDEX
    Explanations

    mathematical 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
    ersed
    -0.08
    erah
    -0.08
    кали
    -0.08
    oola
    -0.08
    lev
    -0.07
     |:
    -0.07
    indah
    -0.07
    åįİåºŃ
    -0.07
    åĪĨ享åĪ°æľĭåıĭåľĪ
    -0.07
    licant
    -0.07
    POSITIVE LOGITS
     Ùĩد
    0.07
    åĮºåĨħ
    0.07
    åĬłä¸Ĭ
    0.07
    ubl
    0.07
    ipot
    0.06
    ä¿Ŀ
    0.06
    åĮºåŁŁåĨħçļĦ
    0.06
    åĮºçļĦ
    0.06
    åĨįåĬłä¸Ĭ
    0.06
    ç»ij
    0.06
    Activations Density 0.011%

    No Known Activations