© 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. 31071
    Prev
    Next
    INDEX
    Explanations

    multiplication and multiplication operations

    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
    armi
    -0.07
    resta
    -0.07
    reb
    -0.07
    ingan
    -0.07
    sche
    -0.07
    inga
    -0.06
    ston
    -0.06
    ortal
    -0.06
    phem
    -0.06
    à¸Ĺà¹Į
    -0.06
    POSITIVE LOGITS
     multiplication
    0.08
    enius
    0.08
    ultip
    0.08
    enner
    0.07
    /div
    0.07
    chtig
    0.07
    licative
    0.07
    Listing
    0.07
    /shop
    0.07
    rauch
    0.07
    Activations Density 0.016%

    No Known Activations