© 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. 16640
    Prev
    Next
    INDEX
    Explanations

    phrasing for verbs and participles

    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
    صاد
    -0.05
    ÙĪÙĥ
    -0.05
    ura
    -0.05
    ruz
    -0.05
    arak
    -0.05
     اÙĦØ´ÙĬØ¡
    -0.05
     пого
    -0.05
     Balk
    -0.05
    yk
    -0.05
    fully
    -0.05
    POSITIVE LOGITS
     Ving
    0.07
    afil
    0.07
     Япо
    0.06
    梦éĩĮ
    0.06
    hejiang
    0.06
     zove
    0.06
    pais
    0.06
    leaflet
    0.06
    _FUN
    0.06
    elib
    0.06
    Activations Density 0.008%

    No Known Activations