© 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. 22413
    Prev
    Next
    INDEX
    Explanations

    v. Plaintiff

    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
    æij©
    -0.06
    amma
    -0.06
     constituent
    -0.06
    ice
    -0.05
    ÙĪ
    -0.05
    folger
    -0.05
    à¸Ŀาà¸ģ
    -0.05
    umph
    -0.05
    趾
    -0.05
    æķĪæŀľçļĦ
    -0.05
    POSITIVE LOGITS
    iran
    0.06
    catch
    0.06
     scad
    0.06
    ought
    0.06
     scramble
    0.06
    åĬ¡å®ŀ
    0.05
    rochen
    0.05
     زاÙĦت
    0.05
    मान
    0.05
    éĻ£
    0.05
    Activations Density 0.002%

    No Known Activations