© 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. 51423
    Prev
    Next
    INDEX
    Explanations

    solve mathematical equations

    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
     interchange
    -0.07
    åĽĽå°Ħ
    -0.06
    Õ²
    -0.06
    ìŀ¬
    -0.06
     procéd
    -0.06
     tab
    -0.06
    Ĺ
    -0.06
    flas
    -0.06
    rink
    -0.06
     Prze
    -0.06
    POSITIVE LOGITS
    جÙĬ
    0.08
     isNaN
    0.08
    letic
    0.07
    ardown
    0.07
    appendChild
    0.07
    satz
    0.07
    ourcing
    0.07
    escu
    0.07
    æĸ¹ç¨ĭ
    0.07
     equation
    0.07
    Activations Density 0.022%

    No Known Activations