© 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. 22567
    Prev
    Next
    INDEX
    Explanations

    CSS properties

    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
    Negative Logits
    ascar
    -0.06
    an
    -0.06
    çŃ
    -0.06
    tml
    -0.06
    æ´ĭæ´ĭ
    -0.05
     Mondial
    -0.05
     thôi
    -0.05
    -Fi
    -0.05
     Enth
    -0.05
     Arlington
    -0.05
    POSITIVE LOGITS
    ekat
    0.06
    oknak
    0.06
    czas
    0.05
    éĤĢ
    0.05
    åľ¨æīĢæľī
    0.05
     ajar
    0.05
    åŃIJåĴĮ
    0.05
    okra
    0.05
    TRACT
    0.05
    .ok
    0.05
    Activations Density 0.006%

    No Known Activations