© 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. 50915
    Prev
    Next
    INDEX
    Explanations

    multiply, division, calculation

    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
    оне
    -0.08
    åħľ
    -0.07
     vs
    -0.07
    åIJĪçIJĨåĪ©çĶ¨
    -0.07
    ä¸įèĩ³äºİ
    -0.06
    usern
    -0.06
    _ALLOW
    -0.06
     Non
    -0.06
    raft
    -0.06
     fern
    -0.06
    POSITIVE LOGITS
     multiplying
    0.12
    åħ¬å¼ı
    0.11
    multiply
    0.11
     multiply
    0.11
    计ç®Ĺåħ¬å¼ı
    0.11
     Multiply
    0.10
     multiplication
    0.10
    Multiply
    0.10
     multiplied
    0.10
     formula
    0.10
    Activations Density 0.019%

    No Known Activations