© 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. 16558
    Prev
    Next
    INDEX
    Explanations

    units of time and structure

    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
    vall
    -0.06
    樣
    -0.06
    åı¬éĽĨ
    -0.06
    azzi
    -0.06
    aiser
    -0.05
     sis
    -0.05
    çĽĹ
    -0.05
    ausal
    -0.05
    ãĢģ
    -0.05
     vaz
    -0.05
    POSITIVE LOGITS
    at
    0.05
    æ¯Ķä½ł
    0.05
    让å°ı
    0.05
    alk
    0.05
    æ¯Ķèĩªå·±
    0.05
    ag
    0.05
    缸çŃī
    0.05
     ÐľÐ°ÑĤеÑĢиал
    0.05
    anta
    0.05
    Th
    0.05
    Activations Density 0.058%

    No Known Activations