© 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. 44388
    Prev
    Next
    INDEX
    Explanations

    plasmid identifiers

    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
    让ä¸ĸçķĮ
    -0.07
     Nez
    -0.07
    arro
    -0.07
     khúc
    -0.07
     coal
    -0.07
    eff
    -0.06
    Unary
    -0.06
    alist
    -0.06
    æ¨
    -0.06
     alist
    -0.06
    POSITIVE LOGITS
    è½½ä½ĵ
    0.08
    rund
    0.08
    è½½
    0.08
    æīĢè½½
    0.08
    为载ä½ĵ
    0.08
    ://%
    0.08
    è¼ī
    0.08
     containing
    0.08
    borgen
    0.07
     DNA
    0.07
    Activations Density 0.044%

    No Known Activations