© 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. 22551
    Prev
    Next
    INDEX
    Explanations

    most or greatest followed by adjective/noun

    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
    aku
    -0.06
    ke
    -0.06
    olding
    -0.05
    mitt
    -0.05
    pret
    -0.05
     Naw
    -0.05
    ()
    -0.05
    åįī
    -0.05
    ologically
    -0.05
    æĦıä¹ī
    -0.05
    POSITIVE LOGITS
    en
    0.06
    åı¯ä»¥æł¹æį®èĩªå·±çļĦ
    0.06
    raub
    0.06
    urre
    0.06
    ÑĩаÑĤ
    0.06
    Ñįд
    0.06
    uten
    0.06
    اÙĨ
    0.06
    hein
    0.06
    etos
    0.06
    Activations Density 0.019%

    No Known Activations