© 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. 16879
    Prev
    Next
    INDEX
    Explanations

    dates and events

    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
    reg
    -0.06
    éĩĮéĿ¢æľī
    -0.05
    kut
    -0.05
    éĢ¢
    -0.05
    let
    -0.05
    ries
    -0.05
    leton
    -0.05
    kön
    -0.05
    illum
    -0.05
    çīĽçļ®
    -0.05
    POSITIVE LOGITS
    izzi
    0.06
    ä¸Ģ身
    0.06
    istration
    0.06
    ido
    0.06
    à¥įà¤Ł
    0.06
     unveil
    0.06
    than
    0.06
    纲
    0.06
    imited
    0.06
    ìĦľ
    0.06
    Activations Density 0.001%

    No Known Activations