© 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. 21809
    Prev
    Next
    INDEX
    Explanations

    Zack Davies, Chuck Grass, new furnace

    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
    umbo
    -0.06
    owns
    -0.06
     contextual
    -0.06
    own
    -0.06
    ubo
    -0.06
     customary
    -0.06
    lemi
    -0.06
    ä¸Ģä¸ªäººåľ¨
    -0.06
    VRT
    -0.05
    มุม
    -0.05
    POSITIVE LOGITS
    å¼ĢæĿ¥
    0.06
    .de
    0.05
     пÑĢимеÑĢ
    0.05
    odia
    0.05
     Herren
    0.05
    çļĦåĴĮ
    0.05
    å¯Ŀ
    0.05
    举ä¾ĭ
    0.05
     handlers
    0.05
    ãģĹãģ¿
    0.05
    Activations Density 0.001%

    No Known Activations