© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22320
    Prev
    Next
    INDEX
    Explanations

    averaging measurements over time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĶ¯æı´
    -0.06
    rowse
    -0.06
     séqu
    -0.06
    èĥ½æ»¡è¶³
    -0.06
    æ¸ħæ³ī
    -0.05
    plers
    -0.05
     Terr
    -0.05
    pping
    -0.05
    insky
    -0.05
     satur
    -0.05
    POSITIVE LOGITS
     averaged
    0.09
     averages
    0.09
     averaging
    0.08
     Aver
    0.07
     stead
    0.07
     consensus
    0.06
    å¹³åĿĩåĢ¼
    0.06
     average
    0.06
    å¹³åĿĩ
    0.06
    aver
    0.06
    Activations Density 0.069%

    No Known Activations