© 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. 22493
    Prev
    Next
    INDEX
    Explanations

    interval sequence, step, increment, decrement

    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
     poj
    -0.06
    å¯¹æľ¬
    -0.06
    ason
    -0.06
    转åĮĸæĪIJ
    -0.06
    åĽ´
    -0.06
    æĪĺ士
    -0.05
     liqu
    -0.05
    åł
    -0.05
    ç»ĵåIJĪ
    -0.05
    à¸ģรà¸Ńà¸ļ
    -0.05
    POSITIVE LOGITS
    elin
    0.06
     stride
    0.06
    lear
    0.06
    uras
    0.06
    éĮ
    0.06
     skipped
    0.05
     skip
    0.05
    lin
    0.05
    çı
    0.05
    relev
    0.05
    Activations Density 0.017%

    No Known Activations