© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11117
    Prev
    Next
    INDEX
    Explanations

    spectra, coherence, frequencies

    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
    redo
    -0.08
    ETR
    -0.08
    Ŀ
    -0.07
    çĶŁæ´»æ°´å¹³
    -0.07
    \db
    -0.07
    elat
    -0.07
    uls
    -0.07
    alic
    -0.07
    uel
    -0.07
    prompt
    -0.07
    POSITIVE LOGITS
    é¢ijè°±
    0.11
     spectra
    0.10
     spectrum
    0.10
     spectral
    0.10
     spek
    0.09
     Spek
    0.09
    requencies
    0.09
     Fourier
    0.09
     Frequ
    0.09
     frequencies
    0.08
    Activations Density 0.010%

    No Known Activations