© 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. 22367
    Prev
    Next
    INDEX
    Explanations

    pyl

    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
    åľ¨æ°´ä¸Ń
    -0.07
    çŃIJ
    -0.07
     phẩm
    -0.06
    tock
    -0.06
    åľ¨æĹ¥å¸¸
    -0.06
    楽ãģĹãĤģãģ¾ãģĻ
    -0.06
    onnier
    -0.06
    çµ¹
    -0.06
    åľ¨æ°´éĩĮ
    -0.06
    loth
    -0.06
    POSITIVE LOGITS
     alc
    0.05
    æ¶Ī
    0.05
    obl
    0.05
     Hp
    0.05
    æĽ´æľīæķĪ
    0.05
    abit
    0.05
     favicon
    0.05
     íŤ
    0.05
     erad
    0.05
    çĶŁæĢģåľĪ
    0.05
    Activations Density 0.023%

    No Known Activations