© 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. 22606
    Prev
    Next
    INDEX
    Explanations

    three

    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
    omen
    -0.06
    å§ĭ
    -0.06
    åŁº
    -0.05
     orient
    -0.05
     اÙĦÙĩا
    -0.05
    æĬĬåŃ©åŃIJ
    -0.05
    tingham
    -0.05
     Schl
    -0.05
     hypo
    -0.05
    riors
    -0.05
    POSITIVE LOGITS
    fur
    0.06
    pan
    0.06
    pun
    0.05
    èĸ
    0.05
    pane
    0.05
     methods
    0.05
    ARC
    0.05
    adura
    0.05
    纵
    0.05
    çģĮ
    0.05
    Activations Density 0.029%

    No Known Activations