© 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. 18317
    Prev
    Next
    INDEX
    Explanations

    nerdy guy

    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
     tạm
    -0.06
     unexpectedly
    -0.06
    Ñģов
    -0.06
     temporarily
    -0.06
    arfs
    -0.06
    æ¼ı
    -0.06
    idé
    -0.06
    åĶ®
    -0.06
     sko
    -0.06
     pleasantly
    -0.06
    POSITIVE LOGITS
    è¿ĽéĢĢ
    0.06
    çºłç»ĵ
    0.06
     resolution
    0.05
    issimo
    0.05
    å¦ĤåIJĮ
    0.05
    é¼İ
    0.05
     perplex
    0.05
    解åĨ³éĹ®é¢ĺçļĦ
    0.05
    asin
    0.05
     reput
    0.05
    Activations Density 0.085%

    No Known Activations