© 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. 51045
    Prev
    Next
    INDEX
    Explanations

    exponentiation and mathematical powers

    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
    áĥļáĥĿáĥij
    -0.08
    eldorf
    -0.07
    áŀĬáŁĤ
    -0.07
    åIJijåħļ
    -0.07
    æ³Ĭ
    -0.07
    åħ¶éģĵ
    -0.07
    way
    -0.07
    åĽĽæĸ¹
    -0.06
    /fw
    -0.06
    æĻļ
    -0.06
    POSITIVE LOGITS
    abu
    0.08
    aset
    0.07
    è¿İæĺ¥
    0.07
    ropy
    0.07
    ossi
    0.07
    agma
    0.07
    åıĪä¸Ģ个
    0.07
    ahu
    0.07
    çŃīåĪ°äºĨ
    0.07
    omentum
    0.07
    Activations Density 0.001%

    No Known Activations