© 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. 22352
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by parenthesis

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ridge
    -0.05
    veal
    -0.05
    quo
    -0.05
     précisé
    -0.05
     Fighting
    -0.05
     Visite
    -0.05
     vivant
    -0.05
    endeu
    -0.05
    attach
    -0.05
    幫
    -0.05
    POSITIVE LOGITS
    ub
    0.06
     :],
    0.06
    è¯Ħ为
    0.06
    ifiant
    0.06
    ABLE
    0.06
    uban
    0.06
    à¹Ģหล
    0.06
    å·
    0.05
    æĽ´å¤ļçļĦæĺ¯
    0.05
    ä¸Ģæŀļ
    0.05
    Activations Density 0.138%

    No Known Activations