© 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. 22393
    Prev
    Next
    INDEX
    Explanations

    command parameters

    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
    ysel
    -0.06
     Autore
    -0.06
    Å¡nj
    -0.06
    yne
    -0.06
    åIJįæĢĿ
    -0.06
    ائÙĦ
    -0.06
    ORE
    -0.05
    autore
    -0.05
    çļĦåŃĺåľ¨
    -0.05
    æĸĩ件æĪĸ
    -0.05
    POSITIVE LOGITS
    igs
    0.05
     Lib
    0.05
    æĦĪ
    0.05
    ig
    0.05
    çļĦ空
    0.05
    空空
    0.05
     premia
    0.05
    idia
    0.05
    ug
    0.05
    æīĢéľĢ
    0.05
    Activations Density 0.002%

    No Known Activations