© 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. 13656
    Prev
    Next
    INDEX
    Explanations

    frequency, resonance, oscillation

    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
    éľĸ
    -0.08
    æ¶ĤæĬ¹
    -0.07
    é£İéĽª
    -0.07
    enzi
    -0.07
    å¢ĥçķĮ
    -0.07
    çł¥
    -0.06
    .Out
    -0.06
    menge
    -0.06
     Distrib
    -0.06
     xúc
    -0.06
    POSITIVE LOGITS
    é¢ijçİĩ
    0.11
    å¤§æľ¬
    0.09
     reson
    0.09
     frequencies
    0.09
     tunes
    0.09
     frequency
    0.09
    frequency
    0.09
    itus
    0.09
     eigen
    0.09
    spring
    0.08
    Activations Density 0.023%

    No Known Activations