© 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. 21586
    Prev
    Next
    INDEX
    Explanations

    variable i in code

    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
    aim
    -0.05
    reta
    -0.05
    runde
    -0.05
    çļĦæĹ¥åŃIJ
    -0.05
    ÙĤÙĬ
    -0.05
    循çݯ
    -0.05
    rack
    -0.05
    çݯèĬĤ
    -0.05
    æĻ¦
    -0.05
    éĿ¶
    -0.05
    POSITIVE LOGITS
    onnal
    0.06
    otis
    0.06
    æĬ¢ä¿®
    0.05
    ä¹ĭ大
    0.05
     melt
    0.05
     refuge
    0.05
     doy
    0.05
    纯æ£ī
    0.05
     اÙĦÙħÙĤا
    0.05
    cul
    0.05
    Activations Density 0.006%

    No Known Activations