© 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. 22488
    Prev
    Next
    INDEX
    Explanations

    url paths and scientific/document references

    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
    åı«
    -0.06
    éģĩ
    -0.06
    Ùĩ
    -0.06
    âĢ
    -0.05
    ium
    -0.05
    iones
    -0.05
    .
    -0.05
    idor
    -0.05
    ennes
    -0.05
    uru
    -0.05
    POSITIVE LOGITS
    tip
    0.07
     siapapun
    0.06
    使çĶ¨ä¸Ń
    0.06
    Pat
    0.06
    æŁ¥æŁ¥
    0.06
    à¹Ģà¸Ľà¸¥à¹Īา
    0.06
     hilf
    0.06
    YLE
    0.06
    æķ°éĩı为
    0.06
    'Neill
    0.06
    Activations Density 0.193%

    No Known Activations