© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19644
    Prev
    Next
    INDEX
    Explanations

    orthopedists or specific medical contexts

    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
    大éĩij
    -0.07
    opin
    -0.06
    æĸ°ç¤¾
    -0.06
    ä¸įåĢĴ
    -0.06
    ä¾ĥ
    -0.06
    æĥ©
    -0.06
    assel
    -0.06
    alink
    -0.06
    åħ¶ä»ĸåľ°åĮº
    -0.06
    ormais
    -0.06
    POSITIVE LOGITS
    æģ¯
    0.06
    net
    0.06
     '
    0.05
    ton
    0.05
    erg
    0.05
    ä¸ĵ注
    0.05
    anh
    0.05
     composed
    0.05
    çī©
    0.05
    å±Ģ
    0.05
    Activations Density 0.001%

    No Known Activations