© 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. 17221
    Prev
    Next
    INDEX
    Explanations

    looping constructs

    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
    ç®ĢåįķçļĦ
    -0.06
    åIJijæĹ¥
    -0.05
    ivist
    -0.05
    éĢIJ
    -0.05
    ä¸ĢéĿ¢
    -0.05
     tact
    -0.05
    habi
    -0.05
    æĹłè¯ģ
    -0.05
     onboard
    -0.05
     simple
    -0.05
    POSITIVE LOGITS
    代表çļĦ
    0.06
    代表
    0.06
    represent
    0.06
    ilh
    0.06
    èģª
    0.06
    zis
    0.06
    åĦĴ
    0.06
    Ùģس
    0.05
    å¹½
    0.05
     representatives
    0.05
    Activations Density 0.013%

    No Known Activations