© 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. 20253
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structure

    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
     favor
    -0.06
    oplan
    -0.06
    çĸij
    -0.06
     favour
    -0.06
     avoided
    -0.06
     mon
    -0.05
     cim
    -0.05
    ои
    -0.05
     favored
    -0.05
    è¿ŀ
    -0.05
    POSITIVE LOGITS
    éģ¥éģ¥
    0.07
    æĹłè®ºä»İ
    0.06
    æĹłè®ºåľ¨
    0.06
    æĹłè®º
    0.06
    æ»ŀ
    0.06
    å¿ħ须注æĺİ
    0.05
    hj
    0.05
    空头
    0.05
    èĻ½çĦ¶åľ¨
    0.05
    åķ¼
    0.05
    Activations Density 0.050%

    No Known Activations