© 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. 1012
    Prev
    Next
    INDEX
    Explanations

    wavelet analysis and transform

    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
    ettel
    -0.08
    δί
    -0.07
    ä¸įèĩªç¦ģ
    -0.07
    пиÑģа
    -0.07
    Wallet
    -0.07
    deaux
    -0.07
    è¾IJå°Ħ
    -0.07
    anzo
    -0.07
    æ°ijæĶ¿
    -0.06
    èIJį
    -0.06
    POSITIVE LOGITS
    .fft
    0.10
     Fourier
    0.10
    åĪĨæŀIJçļĦ
    0.08
     analysis
    0.08
     FFT
    0.08
    ograms
    0.08
    analysis
    0.08
    åĪĨæŀIJ
    0.08
     Decom
    0.08
    æįķæįī
    0.08
    Activations Density 0.031%

    No Known Activations