© 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. 20101
    Prev
    Next
    INDEX
    Explanations

    an adjective

    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
    ä¸īè§Ĵ
    -0.05
     regolar
    -0.05
    åģļå¾Ĺ
    -0.05
    ÑĢек
    -0.05
    æĹ·
    -0.05
    etzes
    -0.05
    æ´»å¾Ĺ
    -0.05
    vens
    -0.05
    spe
    -0.05
    å½¢
    -0.05
    POSITIVE LOGITS
    بس
    0.06
    ä¹ħèĢĮ
    0.06
    idor
    0.06
    namen
    0.06
     genie
    0.06
     Scientist
    0.06
    次ä¼ļè®®
    0.06
     inneb
    0.06
    óf
    0.05
     ÑĦеÑģÑĤива
    0.05
    Activations Density 0.002%

    No Known Activations