© 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. 30112
    Prev
    Next
    INDEX
    Explanations

    Fourier 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
    ÑĥÑĢо
    -0.09
    erator
    -0.09
    erma
    -0.09
    ustry
    -0.08
    iones
    -0.08
    otti
    -0.08
    ltk
    -0.08
    åĴĮçī¹çĤ¹
    -0.08
    ño
    -0.08
    ppure
    -0.08
    POSITIVE LOGITS
    ัà¸ĩ
    0.07
    lhe
    0.07
    roc
    0.07
    ì¼
    0.07
    arty
    0.06
     Springs
    0.06
    insel
    0.06
    ack
    0.06
    ergus
    0.06
    tement
    0.06
    Activations Density 0.006%

    No Known Activations