© 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. 3668
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers and divisions

    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
    اÙĨس
    -0.08
     boite
    -0.07
    aser
    -0.07
    upes
    -0.07
    REN
    -0.07
    ades
    -0.07
    .hu
    -0.07
    emis
    -0.07
    ected
    -0.07
    av
    -0.07
    POSITIVE LOGITS
    ç¤
    0.07
     Peg
    0.07
    alani
    0.07
    eiÃŁ
    0.07
    iskan
    0.07
    ÃŃfica
    0.06
    åĦ¿æŶ
    0.06
    oons
    0.06
    éłĵ
    0.06
    steuer
    0.06
    Activations Density 0.030%

    No Known Activations