© 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. 16779
    Prev
    Next
    INDEX
    Explanations

    diagnostic classification manuals (DSM, WHO)

    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
     tempr
    -0.05
    åħ¨å¤©
    -0.05
     security
    -0.05
     hao
    -0.05
     занÑıÑĤ
    -0.05
    天çĦ¶çļĦ
    -0.05
    ssen
    -0.05
    hell
    -0.05
     existen
    -0.05
    life
    -0.05
    POSITIVE LOGITS
    unge
    0.06
    -awaited
    0.06
    ópez
    0.06
    à¸ķู
    0.05
    æĮĩåįĹ
    0.05
    æĢ§è¡Į为
    0.05
    éĺ³çĹ¿
    0.05
     salg
    0.05
    èĭŀ
    0.05
    éĩĬ
    0.05
    Activations Density 0.042%

    No Known Activations