© 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. 21231
    Prev
    Next
    INDEX
    Explanations

    fft, division, transforms

    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
    éĢĢ缩
    -0.07
    aze
    -0.07
     Habit
    -0.07
    ç¬ĭ
    -0.07
     dri
    -0.06
    gaz
    -0.06
    lt
    -0.06
    ieden
    -0.06
    hab
    -0.06
     ign
    -0.06
    POSITIVE LOGITS
     FFT
    0.13
    .fft
    0.11
     Fourier
    0.11
    _fft
    0.11
    FFT
    0.10
     fft
    0.09
    åĤħ
    0.09
    USIC
    0.09
    fft
    0.08
     radix
    0.08
    Activations Density 0.012%

    No Known Activations