© 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. 17337
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    /mit
    -0.07
    ربÛĮ
    -0.07
    peg
    -0.07
    جÙĪÛĮ
    -0.06
    azes
    -0.06
    ãģ®ãģĬåºĹ
    -0.06
    ä»ĸè¿ĺæĺ¯
    -0.06
    han
    -0.06
    меÑĤим
    -0.06
    waran
    -0.06
    POSITIVE LOGITS
    èĩ³
    0.06
    è¡Į
    0.05
    è¿Ķ
    0.05
    ÑĢенд
    0.05
    éĩį
    0.05
     CLOSE
    0.05
    æµijçĦ¶
    0.05
    å¼Ĺ
    0.05
    æĿij
    0.04
    nit
    0.04
    Activations Density 0.000%

    No Known Activations