© 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. 58106
    Prev
    Next
    INDEX
    Explanations

    phonons and modes

    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
    æĹłä»İ
    -0.07
     Flour
    -0.07
    æ·¡èĸĦ
    -0.07
    æ½¢
    -0.07
    æŶ令
    -0.06
    è¡ĢæµĨ
    -0.06
    è¡Ģ迹
    -0.06
    urant
    -0.06
     washed
    -0.06
     marg
    -0.06
    POSITIVE LOGITS
     vibrations
    0.11
     phon
    0.11
    phon
    0.10
     vibration
    0.10
    æĮ¯åĬ¨
    0.09
     vibr
    0.09
     Phon
    0.09
    åĿĤ
    0.08
     вибÑĢа
    0.08
    empa
    0.08
    Activations Density 0.013%

    No Known Activations