© 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. 18648
    Prev
    Next
    INDEX
    Explanations

    to acquire or create

    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
    åĵŃäºĨ
    -0.06
    æŃ¤èµ·
    -0.06
    tidig
    -0.06
    eted
    -0.06
    è±ģ
    -0.06
    imd
    -0.06
    wic
    -0.06
    工夫
    -0.06
    ä½ıæ°ij
    -0.06
    è¨Ĺ
    -0.06
    POSITIVE LOGITS
    o
    0.06
     -
    0.05
    (?)
    0.05
    s
    0.05
    aggi
    0.05
     spol
    0.05
    0.05
    çļĦä¸ĢäºĽ
    0.05
    æľīå¾Ī强çļĦ
    0.05
     عÙĦا
    0.05
    Activations Density 0.087%

    No Known Activations