© 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. 16684
    Prev
    Next
    INDEX
    Explanations

    to change

    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
    ption
    -0.06
    stra
    -0.06
    天ä¸ĭçļĦ
    -0.06
    ('/')[-
    -0.06
    ê°ģ
    -0.06
    apos
    -0.06
    idious
    -0.06
    gestion
    -0.05
    chaft
    -0.05
    à¹Īà¸Ńย
    -0.05
    POSITIVE LOGITS
    ç¿¡
    0.05
    åĬĽæīĢèĥ½åıĬ
    0.05
     imread
    0.05
    itano
    0.05
    ucky
    0.05
    سÙĪب
    0.05
    ulo
    0.04
    ano
    0.04
    æľ¬éĥ¨
    0.04
    <u
    0.04
    Activations Density 0.001%

    No Known Activations