© 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. 39522
    Prev
    Next
    INDEX
    Explanations

    noise and spectra

    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
    anz
    -0.07
    ä¸ĭåŃ¦æľŁ
    -0.07
    ulet
    -0.07
    eut
    -0.07
    çĥ¨
    -0.07
    bote
    -0.07
    yson
    -0.07
     intptr
    -0.06
    Paren
    -0.06
    Clickable
    -0.06
    POSITIVE LOGITS
    åĻªå£°
    0.11
     noise
    0.11
     Noise
    0.10
    noise
    0.09
    æºIJ头
    0.09
    é¢ijè°±
    0.09
    Noise
    0.09
     ruido
    0.09
    æºIJæ³ī
    0.09
     hiss
    0.09
    Activations Density 0.009%

    No Known Activations