© 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. 22419
    Prev
    Next
    INDEX
    Explanations

    has been

    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
    æŃ»ä¸į
    -0.07
    ager
    -0.06
    innie
    -0.06
    age
    -0.06
    à¹ģลà¹īววà¹Īา
    -0.06
    odore
    -0.06
    åľ¨åIJĮ
    -0.06
     vaat
    -0.06
    Ñĩайно
    -0.06
    жев
    -0.06
    POSITIVE LOGITS
    æĽ´å¤§
    0.05
    ihe
    0.05
    åĨį
    0.05
     sake
    0.05
     Begins
    0.05
    ibil
    0.05
     stav
    0.05
     matters
    0.05
     either
    0.05
    ellen
    0.05
    Activations Density 0.007%

    No Known Activations