© 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. 22474
    Prev
    Next
    INDEX
    Explanations

    conference names and organizations

    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
    èĦ
    -0.07
    ipa
    -0.06
    ä¸įéĹ®
    -0.06
    éĿ¢éĿ¢
    -0.06
    unden
    -0.06
    åı¥åı¥
    -0.06
    igned
    -0.06
    depend
    -0.06
    ferences
    -0.06
    ç¦ģ令
    -0.05
    POSITIVE LOGITS
    è¿ĻæĦıåij³çĿĢ
    0.06
    çļĦæĦıæĢĿæĺ¯
    0.06
    oster
    0.06
    è¿Ļæĺ¯ä¸Ģç§į
    0.05
    åĢŁæѤ
    0.05
    ading
    0.05
    oti
    0.05
    æĦıåij³çĿĢ
    0.05
    tock
    0.05
     yourself
    0.05
    Activations Density 0.001%

    No Known Activations