© 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. 16749
    Prev
    Next
    INDEX
    Explanations

    mathematical problem starters

    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
    achu
    -0.06
    ergen
    -0.05
    ä¸İ大
    -0.05
    éĥ¨ç½²
    -0.05
    çļĦè¡ĮåĬ¨
    -0.05
    rette
    -0.05
    Luckily
    -0.05
    essian
    -0.05
    adder
    -0.05
    ä¸Ĭä¸ĭ
    -0.05
    POSITIVE LOGITS
     usc
    0.06
    ä¸Ńè§Ħ
    0.06
    عاÙĦ
    0.06
    æĥľ
    0.06
    áĢĢáĢ¹
    0.06
    hares
    0.06
    Õ¡Öģ
    0.05
    Bloc
    0.05
    воз
    0.05
    nun
    0.05
    Activations Density 0.007%

    No Known Activations