© 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. 21805
    Prev
    Next
    INDEX
    Explanations

    structural punctuation and 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
     ÐłÐ°Ð´Ð¸
    -0.06
    yas
    -0.06
    schlieÃŁ
    -0.06
    äºĮ代
    -0.06
    æv
    -0.05
     Radi
    -0.05
    并éĩĩåıĸ
    -0.05
    ä»ĬåIJİ
    -0.05
     ÑĢади
    -0.05
     gewähr
    -0.05
    POSITIVE LOGITS
    quist
    0.06
    u
    0.05
     controvers
    0.05
    berg
    0.05
    vie
    0.05
    olly
    0.05
    غÙĬ
    0.05
    æł¹æľ¬
    0.05
    lic
    0.05
     sett
    0.05
    Activations Density 0.018%

    No Known Activations