© 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. 19921
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and punctuation

    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
    å°Ķæĸ¯
    -0.06
    åĮł
    -0.06
    åħ·
    -0.06
    cess
    -0.05
    ä½įåľ¨
    -0.05
    kses
    -0.05
    æĬ½ç©º
    -0.05
    ãģıãģłãģķãģĦãģŃ
    -0.05
    hes
    -0.05
    ä¸Ī
    -0.05
    POSITIVE LOGITS
    é£
    0.07
    éŃĦ
    0.06
    æ¯ıä¸ĢæĿ¡
    0.06
    åįģäºĶæĿ¡
    0.06
     Spur
    0.06
     BUR
    0.06
    åĽĽæĿ¡
    0.06
    erber
    0.06
    peÄį
    0.06
     dele
    0.06
    Activations Density 0.024%

    No Known Activations