© 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. 16698
    Prev
    Next
    INDEX
    Explanations

    programming, development, remodeling, imaging, processing, disposal, delivery

    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
    管æīĢ
    -0.07
    pei
    -0.06
    ajian
    -0.06
    æĥħæľī
    -0.06
    engel
    -0.06
     arran
    -0.05
    áng
    -0.05
    ове
    -0.05
    à¦ĵয়া
    -0.05
    _$
    -0.05
    POSITIVE LOGITS
    rightness
    0.05
    uida
    0.05
    Than
    0.05
    owing
    0.05
    cr
    0.05
    à¹ģà¸ķà¹Īà¸Ń
    0.05
    else
    0.05
    cura
    0.05
    éĥ½æľīä¸įåIJĮçļĦ
    0.05
    西åĮ»
    0.05
    Activations Density 0.067%

    No Known Activations