© 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. 21566
    Prev
    Next
    INDEX
    Explanations

    NegativeButton, Den, den, Taylor

    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
    를
    -0.09
    çļĦ
    -0.07
    æł·åŃIJ
    -0.06
    ÛĮ
    -0.06
    less
    -0.06
    ,
    -0.06
    \
    -0.06
    为ä¸Ģ
    -0.06
    am
    -0.06
    ãģĹãģ¾ãģĨ
    -0.06
    POSITIVE LOGITS
    ÑģлÑĮ
    0.09
    جاÙĨ
    0.08
    ยิà¹Īà¸ĩ
    0.08
    нÑıÑĤно
    0.07
     artifici
    0.07
    à¸ŀาะ
    0.07
    abyrinth
    0.07
    apsed
    0.07
    raph
    0.07
    ician
    0.07
    Activations Density 0.005%

    No Known Activations