© 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. 56188
    Prev
    Next
    INDEX
    Explanations

    pulses or waveforms

    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
    ç³»
    -0.09
    getDefault
    -0.08
    纵横
    -0.08
    å®ŀåIJį
    -0.07
    ç³»çļĦ
    -0.07
     hier
    -0.07
    orado
    -0.07
    weigh
    -0.07
     hierarchical
    -0.07
     cpt
    -0.07
    POSITIVE LOGITS
     impulses
    0.08
    æ¯ıä¸Ģ次
    0.08
     waveform
    0.08
    æľĪæľĪ
    0.08
    è¿ŀç»ŃçļĦ
    0.08
    ecycle
    0.08
    ä¸įåĢĴ
    0.08
     swings
    0.08
    ulses
    0.08
    äº¤æĽ¿
    0.07
    Activations Density 0.009%

    No Known Activations