© 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. 17843
    Prev
    Next
    INDEX
    Explanations

    method, property, or code block definitions

    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
    è¸Ĭ
    -0.06
    åIJĦçݯèĬĤ
    -0.06
    igre
    -0.06
    iono
    -0.06
    ekl
    -0.06
    icket
    -0.06
    aszt
    -0.06
    åIJĦæĸ¹éĿ¢çļĦ
    -0.06
    isser
    -0.06
    è²¢
    -0.06
    POSITIVE LOGITS
    ards
    0.05
    å¼Ĺ
    0.05
    cept
    0.05
     incur
    0.05
    为æŃ¢
    0.05
    ard
    0.05
    apon
    0.05
    æł·çļĦ
    0.05
     polos
    0.05
    INED
    0.05
    Activations Density 0.002%

    No Known Activations