© 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. 16645
    Prev
    Next
    INDEX
    Explanations

    word or words

    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
    chein
    -0.06
    aset
    -0.06
    ECK
    -0.06
    ligt
    -0.06
    .writerow
    -0.06
    laÄį
    -0.06
    严éĩįè¿Ŀæ³ķ
    -0.06
    éĢļè¿ĩæľ¬æ¬¡
    -0.06
     sicil
    -0.06
    iggins
    -0.06
    POSITIVE LOGITS
    *
    0.05
     longest
    0.05
     longer
    0.05
    ↵
    0.05
     thorough
    0.05
     R
    0.05
    æĹłæķĮ
    0.05
     ↵
    0.05
    éĺ
    0.05
     L
    0.04
    Activations Density 0.008%

    No Known Activations