© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19260
    Prev
    Next
    INDEX
    Explanations

    C++ `::` or Python `.` syntax

    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
    大æī¹
    -0.06
    vider
    -0.06
    é«ĺéĢŁ
    -0.06
    å¿ĥå¢ĥ
    -0.06
    .stringify
    -0.06
    kohol
    -0.06
    ìłIJìľ¼ë¡ľ
    -0.06
    åħ¨æľ¬
    -0.06
    untut
    -0.06
    unica
    -0.06
    POSITIVE LOGITS
    ä¸įåı¯
    0.07
    ä¸įæĪIJ
    0.06
    åıĹ
    0.06
    ä¸įèĩª
    0.06
    缮åīį
    0.06
     soph
    0.05
    çĭ¬ç«ĭ
    0.05
     redeem
    0.05
    æŀĦæĪIJ
    0.05
    ä¾Ŀèµĸ
    0.05
    Activations Density 0.003%

    No Known Activations