© 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. 20715
    Prev
    Next
    INDEX
    Explanations

    specific lists often followed by descriptive terms or categories

    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
    é£ŀ车
    -0.06
    ennifer
    -0.05
    격
    -0.05
    olor
    -0.05
    ä¸İä¼łç»Ł
    -0.05
    æİĪ
    -0.05
    åºĶçĶ¨é¢ĨåŁŁ
    -0.05
    æĮīçħ§
    -0.05
     ".",
    -0.05
    expo
    -0.05
    POSITIVE LOGITS
    åıĪå¤ļ
    0.06
    çij
    0.05
     sẵn
    0.05
     Purtroppo
    0.05
     tamb
    0.05
    ucia
    0.05
    icza
    0.05
     okazji
    0.05
     didn
    0.05
     ÙĥØ°ÙĦÙĥ
    0.05
    Activations Density 0.012%

    No Known Activations