© 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. 21042
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence start

    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
    onne
    -0.06
    kens
    -0.06
    راث
    -0.06
    اÙħÙĦ
    -0.06
    е
    -0.06
     PREMI
    -0.06
     susceptible
    -0.06
    robi
    -0.06
    geries
    -0.06
     kupon
    -0.06
    POSITIVE LOGITS
    çIJĨæŁ¥
    0.05
    羣çIJĨ
    0.05
    åľ¨åĮĹ京
    0.05
    åĢ¼
    0.05
    æĪij们è¦ģ
    0.05
    è¯Ŀ
    0.05
    otra
    0.05
    ÑĥÑģа
    0.04
    çIJĨä¼ļ
    0.04
    åľ¨ä¸Ĭæµ·
    0.04
    Activations Density 0.029%

    No Known Activations