© 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. 20320
    Prev
    Next
    INDEX
    Explanations

    arriving late

    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
    æĺ¯åIJ¦ä¸İ
    -0.06
    /release
    -0.06
    воÑĢо
    -0.06
    æѦåĻ¨
    -0.06
    æĹ¥ä¸º
    -0.06
    ieras
    -0.05
    æľ¬æĬ¥è®°èĢħ
    -0.05
    æłĪ
    -0.05
    å¼¹åĩº
    -0.05
     Interr
    -0.05
    POSITIVE LOGITS
    è¿ŁåĪ°
    0.07
    è¥Ł
    0.06
     forever
    0.06
    åĢĻ
    0.05
    浸润
    0.05
     ÑģÑĤÑĭ
    0.05
    wait
    0.05
    auff
    0.05
    åĪ°æŶ
    0.05
    .Hosting
    0.05
    Activations Density 0.018%

    No Known Activations