© 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. 34362
    Prev
    Next
    INDEX
    Explanations

    division 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
    vert
    -0.07
    ä¸ĬæīĢ
    -0.06
     spell
    -0.06
    å¾Ĺå½ĵ
    -0.06
    åĮħæĭ¬
    -0.06
    atel
    -0.06
    éĤ¦
    -0.06
    ä¸ĢæľĽ
    -0.06
    ä¸İä½ľçĶ¨
    -0.06
    ë¦ĩ
    -0.06
    POSITIVE LOGITS
    çĴŁ
    0.08
    errer
    0.07
     ourselves
    0.07
     eksk
    0.07
    è¿Ľè¡Įä¸Ģ次
    0.07
    änz
    0.07
    fru
    0.07
    egger
    0.07
    rough
    0.07
    colas
    0.07
    Activations Density 0.009%

    No Known Activations