© 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. 21842
    Prev
    Next
    INDEX
    Explanations

    comparison operators

    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
    åıªæľīä¸Ģ个
    -0.06
    家
    -0.06
    æİ¥ä¸ĭ
    -0.06
    лада
    -0.05
    æľ´ç´ł
    -0.05
    pear
    -0.05
    اتÛĮ
    -0.05
     oda
    -0.05
    stras
    -0.05
    tenzione
    -0.05
    POSITIVE LOGITS
    igny
    0.05
     Beiträge
    0.05
    æļĤæŶ
    0.05
    çľĭå¾Ĺ
    0.05
    enburg
    0.05
    夯å®ŀ
    0.05
    èŃ·
    0.05
     fellow
    0.05
    -il
    0.05
    éĴŀ
    0.05
    Activations Density 0.003%

    No Known Activations