© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16786
    Prev
    Next
    INDEX
    Explanations

    "is as you’d expect"

    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
    Negative Logits
    mare
    -0.06
    åħĭåĪ©
    -0.06
    alist
    -0.06
    æīĢ使çĶ¨çļĦ
    -0.06
    ãĥ¯ãĥ¼
    -0.05
    alba
    -0.05
    ÙģØ´
    -0.05
    ukes
    -0.05
    bern
    -0.05
    æ¾Ħæ¸ħ
    -0.05
    POSITIVE LOGITS
     Dont
    0.06
     subparagraph
    0.06
    ç»
    0.06
    èݹ
    0.06
    ose
    0.05
    ä¸Ģ缴
    0.05
    dbl
    0.05
    пÑĭ
    0.05
     ('\
    0.05
    串
    0.05
    Activations Density 0.001%

    No Known Activations