© 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. 20180
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and pairing

    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
    arian
    -0.06
    ced
    -0.06
    çļĦéĿ¢åŃĶ
    -0.05
    ctic
    -0.05
     devid
    -0.05
    issimi
    -0.05
     tamp
    -0.05
     ultra
    -0.05
     mù
    -0.05
    串
    -0.05
    POSITIVE LOGITS
    åİŁä»¶åıĬ
    0.06
    åºĶæĶ¶
    0.06
     ì·¨
    0.05
    æŃ¤èµ·
    0.05
    ä¸İå·¥ä½ľ
    0.05
    presa
    0.05
    éĺ´åĩī
    0.05
    alone
    0.05
    éĺĸ
    0.05
    åħĥ以ä¸Ĭ
    0.05
    Activations Density 0.002%

    No Known Activations