© 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. 16851
    Prev
    Next
    INDEX
    Explanations

    clear background, set color

    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
    Not in Any Lists

    No Comments

    Negative Logits
    è·¨è¿ĩ
    -0.05
    ekar
    -0.05
    åħ³äºĨ
    -0.05
    ollo
    -0.05
    abs
    -0.05
     ca
    -0.05
    quen
    -0.05
    åľĨåľĨ
    -0.05
    (.)
    -0.05
     quen
    -0.05
    POSITIVE LOGITS
     nghá»ĭch
    0.07
    表éĿ¢
    0.06
    ÄĻż
    0.06
    ullen
    0.05
    å¿Ĺ
    0.05
     armada
    0.05
    表éĿ¢çļĦ
    0.05
    estern
    0.05
    åįİ西
    0.05
     surface
    0.05
    Activations Density 0.003%

    No Known Activations