© 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. 17893
    Prev
    Next
    INDEX
    Explanations

    interface declaration

    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
    ple
    -0.05
    poss
    -0.05
    æĬ¹
    -0.05
    ↵
    -0.05
    X
    -0.05
    æıı
    -0.05
    /
    -0.05
    èĩª
    -0.05
     parap
    -0.04
    1
    -0.04
    POSITIVE LOGITS
    #index
    0.07
    åIJijæĹ¥
    0.07
    wujudkan
    0.07
    //(
    0.07
     ÑıÑĢ
    0.06
    ówczas
    0.06
    ãģ®è²©
    0.06
    druk
    0.06
     ÐĴелико
    0.06
    éĿŀ常ä¸įéĶĻ
    0.06
    Activations Density 0.001%

    No Known Activations