© 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. 51941
    Prev
    Next
    INDEX
    Explanations

    sculptor or sculpture

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ç¼®
    -0.07
    iband
    -0.07
    estre
    -0.07
    纱
    -0.07
    åı£çļĦ
    -0.06
    ä¸Ģè¶Ł
    -0.06
    æĬĬäºĭæĥħ
    -0.06
    辺
    -0.06
    .getColor
    -0.06
    éĩıåŃIJ
    -0.06
    POSITIVE LOGITS
    æł©æł©å¦ĤçĶŁ
    0.11
    å½¢ä½ĵ
    0.10
    å¡ijéĢł
    0.10
    éĽķå¡ij
    0.10
    ulpt
    0.10
    æijĨ件
    0.10
     sculpt
    0.10
     sculpture
    0.10
     statues
    0.10
     statue
    0.09
    Activations Density 0.066%

    No Known Activations