© 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. 21433
    Prev
    Next
    INDEX
    Explanations

    one should use

    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
    ouv
    -0.06
    ustru
    -0.06
    uts
    -0.06
    佬
    -0.06
    riage
    -0.06
    éķ¿åħ´
    -0.05
    utas
    -0.05
     Gefahr
    -0.05
    unge
    -0.05
    åıįèĢĮ
    -0.05
    POSITIVE LOGITS
    ä¸ĩäºĭå¦ĤæĦı
    0.05
    cel
    0.05
    ç½²
    0.05
    é¦ĸ次
    0.05
     Cron
    0.05
    çļĦ第ä¸Ģ个
    0.05
    èī¯
    0.05
    elai
    0.05
    ä¸Ģè¨Ģ
    0.05
    ehler
    0.05
    Activations Density 0.005%

    No Known Activations