© 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. 18557
    Prev
    Next
    INDEX
    Explanations

    digits followed by punctuation or AM

    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
    icum
    -0.06
    vist
    -0.06
    å¿ĥèĤº
    -0.06
    asten
    -0.06
    veyor
    -0.06
     chá»ijn
    -0.06
    vend
    -0.05
    ast
    -0.05
    uert
    -0.05
    ä¸ī级
    -0.05
    POSITIVE LOGITS
    æĪIJè´¥
    0.06
    ül
    0.06
    æĶ¯
    0.05
    γÏģά
    0.05
    ç»ıéªĮ
    0.05
    off
    0.05
    çļĦä¸Ģçŀ¬éĹ´
    0.05
    alise
    0.05
    ли
    0.05
    åĽŀè¿ĩç¥ŀ
    0.05
    Activations Density 0.040%

    No Known Activations