© 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. 29154
    Prev
    Next
    INDEX
    Explanations

    polar coordinates and trigonometry

    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
    ewater
    -0.08
    ikai
    -0.07
    ayani
    -0.06
    oo
    -0.06
    im
    -0.06
    bewert
    -0.06
    ç·Ĵ
    -0.06
    ç·»
    -0.06
     rum
    -0.06
    éĹ®éĹ®
    -0.06
    POSITIVE LOGITS
     sine
    0.07
    åĮĸ解
    0.07
     зда
    0.07
    åħįåİ»
    0.07
     saz
    0.07
     trig
    0.07
    åıĺéĩı
    0.07
     sinh
    0.07
    .Duration
    0.07
    Normalize
    0.07
    Activations Density 0.006%

    No Known Activations