© 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. 17926
    Prev
    Next
    INDEX
    Explanations

    code syntax, programming syntax

    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
    åľ¨æīĢ
    -0.07
    æľŁä¸º
    -0.06
    atih
    -0.06
    artner
    -0.06
    unders
    -0.06
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.06
    ζε
    -0.06
    ä¸į妨
    -0.06
    GED
    -0.06
     ëĮĢíķ´ìĦľëĬĶ
    -0.06
    POSITIVE LOGITS
     bios
    0.06
    unic
    0.05
    åĪ°ä»Ģä¹Ī
    0.05
    lim
    0.05
    å°¼æĸ¯
    0.05
    सार
    0.05
    grade
    0.05
    ophilia
    0.05
    chem
    0.04
    æĢİæł·çļĦ
    0.04
    Activations Density 0.001%

    No Known Activations