© 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. 22318
    Prev
    Next
    INDEX
    Explanations

    priority

    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
    obble
    -0.08
    éĵĽ
    -0.07
    bury
    -0.07
    ceed
    -0.07
    athers
    -0.06
    volv
    -0.06
    ëħ¼
    -0.06
    หัวà¹ĥà¸Ī
    -0.06
    ÙħÙĬزة
    -0.06
    hasil
    -0.06
    POSITIVE LOGITS
    0.06
     -
    0.05
    æľĿ
    0.05
    ãģªãģĭ
    0.05
    ihan
    0.05
    stelling
    0.05
    нин
    0.05
    ness
    0.05
     jet
    0.05
    éĴĪ对
    0.05
    Activations Density 0.003%

    No Known Activations