© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55156
    Prev
    Next
    INDEX
    Explanations

    loop increment `i++`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    aed
    -0.07
    项
    -0.07
    è¶Ł
    -0.07
    urang
    -0.07
    åºĶäºĪ
    -0.07
    andel
    -0.07
     takeaway
    -0.07
    ä¸Ģåıĺ
    -0.06
    antan
    -0.06
    isar
    -0.06
    POSITIVE LOGITS
    립
    0.07
     ÙĪØ¥ÙĦÙī
    0.07
     Burgess
    0.06
    ijker
    0.06
    æłĩå¿Ĺ
    0.06
    ÑĢоÑĤ
    0.06
    ingas
    0.06
    سÙĬÙħ
    0.06
    resenter
    0.06
    crypt
    0.06
    Activations Density 0.013%

    No Known Activations