© 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. 20019
    Prev
    Next
    INDEX
    Explanations

    other than

    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
    alth
    -0.07
    écur
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    æĢ»åĢ¼
    -0.07
    ÅĻÃŃ
    -0.07
    人æĹł
    -0.06
     +'
    -0.06
    ÙĥÙĬØ©
    -0.06
    althy
    -0.06
    ç»°
    -0.06
    POSITIVE LOGITS
     related
    0.06
    ä¸ĢèĪ¬æĿ¥è¯´
    0.05
    vi
    0.05
    ä¸ĢèĪ¬æĺ¯
    0.05
    ä¸ĢèĪ¬çļĦ
    0.05
     either
    0.05
    nt
    0.05
    lag
    0.05
     mainly
    0.04
    ä¸Ģå®ļçļĦ
    0.04
    Activations Density 0.009%

    No Known Activations