© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 6953
    Prev
    Next
    INDEX
    Explanations

    sideband transmission standards

    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
    Negative Logits
    sequence
    -0.08
    æıIJä¾ĽæĽ´å¤ļçļĦ
    -0.08
    städ
    -0.08
    .sequence
    -0.07
    exo
    -0.07
    åĬªåĬĽåģļåĪ°
    -0.07
     поÑįÑĤа
    -0.07
    Sequence
    -0.07
    ç½ijåıĭçļĦ
    -0.07
    对ä»ĸ们çļĦ
    -0.07
    POSITIVE LOGITS
    band
    0.09
     bands
    0.08
    移
    0.08
     band
    0.08
    é¢ij段
    0.08
    æIJ¬
    0.08
     plage
    0.08
    移åĩº
    0.08
    -band
    0.08
    ymmetric
    0.08
    Activations Density 0.011%

    No Known Activations