© 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. 17093
    Prev
    Next
    INDEX
    Explanations

    website addresses or emails

    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
    నిà°ķà°¿
    -0.05
     completely
    -0.05
    æµij身
    -0.05
    à¸Ńà¸ģà¸Īาà¸ģ
    -0.05
    åķĨåĬ¡åIJĪä½ľ
    -0.05
    æ±Łä¸ľ
    -0.05
    æĬļ
    -0.05
    è¡¢
    -0.05
     Hanson
    -0.05
    chest
    -0.05
    POSITIVE LOGITS
    éĩįçĤ¹æĺ¯
    0.06
     mosaic
    0.06
    责任éĻ©
    0.06
    éĻ¢
    0.06
    åħ·ä½ĵåĪĨæŀIJ
    0.06
    ogliamo
    0.05
     cig
    0.05
     kath
    0.05
    åħ³éĶ®çݯèĬĤ
    0.05
    ayer
    0.05
    Activations Density 0.002%

    No Known Activations