© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17355
    Prev
    Next
    INDEX
    Explanations

    this is a/my/your/the

    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
    ä¸İ被
    -0.06
     Beit
    -0.05
    _descriptor
    -0.05
    æĪĸ被
    -0.05
    ç¬Ķä¸ĭçļĦ
    -0.05
     تتÙħÙĥÙĨ
    -0.05
    è¯Ńè¨Ģ表达
    -0.05
    uccio
    -0.05
    ยม
    -0.05
     Europé
    -0.05
    POSITIVE LOGITS
    ame
    0.05
    uchy
    0.05
    ä¸Ģéľĩ
    0.05
     useless
    0.05
    bla
    0.05
    æ²¾
    0.05
    unt
    0.05
    åĪ°æѤ
    0.05
    éĺ²
    0.05
    æľ¬æ³ķ
    0.05
    Activations Density 0.009%

    No Known Activations