© 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. 22376
    Prev
    Next
    INDEX
    Explanations

    eco-friendly, fairtrade, sourcing

    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
    æī¹åĩĨåIJİ
    -0.06
    çĶ³æĬ¥æĿIJæĸĻ
    -0.06
    åĴĢ
    -0.05
    oger
    -0.05
    éģĹ
    -0.05
    å¸Ĥæ°ij
    -0.05
    ä¸ĸ代
    -0.05
    åĪĴ
    -0.05
     Exiting
    -0.05
     abi
    -0.05
    POSITIVE LOGITS
     sourcing
    0.06
    ordan
    0.06
    åĽłç¼ĺ
    0.06
    adaan
    0.06
    å¥Ķèµ´
    0.06
    itti
    0.05
    éĩĩ访æĹ¶è¡¨ç¤º
    0.05
    ç«Ń
    0.05
    追踪
    0.05
     нала
    0.05
    Activations Density 0.020%

    No Known Activations