© 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. 22591
    Prev
    Next
    INDEX
    Explanations

    for loop

    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
     "
    -0.06
     ga
    -0.06
     ↵
    -0.05
     fat
    -0.05
    æī¾åĪ°ä¸Ģ个
    -0.05
    -0.05
    bauer
    -0.05
    åīįè¿°
    -0.05
    anal
    -0.05
    اغ
    -0.05
    POSITIVE LOGITS
    ëĭ¬ëŁ¬
    0.07
    uele
    0.07
     Ulus
    0.07
    verz
    0.07
    à¸Ĺัà¹Īว
    0.06
     freue
    0.06
    achim
    0.06
    ulis
    0.06
     marav
    0.06
    imei
    0.06
    Activations Density 0.003%

    No Known Activations