© 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. 16651
    Prev
    Next
    INDEX
    Explanations

    JSON return statements

    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
     ë°©
    -0.06
    eff
    -0.06
    æķĪ
    -0.06
    fil
    -0.05
    èĽ¾
    -0.05
    æĸ½
    -0.05
    OF
    -0.05
    encontre
    -0.05
     Fil
    -0.05
    bane
    -0.05
    POSITIVE LOGITS
    æĹ©èµ·
    0.06
    resher
    0.06
    zion
    0.06
    pta
    0.06
    ptos
    0.06
    ãģ®ãģĮ
    0.06
     Rolls
    0.05
     piatta
    0.05
    ä¸Ģèģ²
    0.05
    寰
    0.05
    Activations Density 0.003%

    No Known Activations