© 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. 16598
    Prev
    Next
    INDEX
    Explanations

    patent application numbers

    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
    zcze
    -0.07
    åºĹéķĩ
    -0.07
    =length
    -0.07
    оÑĢÑĤи
    -0.07
    æĪijåĪļ
    -0.07
    onse
    -0.06
    .fi
    -0.06
    uzzi
    -0.06
     estrateg
    -0.06
     laga
    -0.06
    POSITIVE LOGITS
    |
    0.05
    "
    0.05
    âĢĮ
    0.05
    âĪ
    0.05
    ()
    0.05
    ↵
    0.05
    åīĸ
    0.05
     Kel
    0.05
    ÂŃ
    0.05
    _
    0.04
    Activations Density 0.006%

    No Known Activations