© 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. 37483
    Prev
    Next
    INDEX
    Explanations

    exceeding thresholds

    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
    è¶Ĭå°ij
    -0.13
    太å°ı
    -0.12
    è¶Ĭå°ı
    -0.11
    è¾ĥè½»
    -0.11
    æ¯Ķè¾ĥå°ı
    -0.11
    太å°ij
    -0.10
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.10
    ä¹Łä¸įå¤ļ
    -0.10
    è¶Ĭä½İ
    -0.10
    åıĺå°ı
    -0.10
    POSITIVE LOGITS
    è¿ľè¶ħ
    0.18
     exceeds
    0.15
     surpass
    0.14
     exceed
    0.13
    è¿ľé«ĺäºİ
    0.13
     exceeding
    0.12
    è¶ħè¿ĩäºĨ
    0.12
    è¶ħè¿ĩ
    0.12
     пÑĢевÑĭÑĪаеÑĤ
    0.12
     exceeded
    0.11
    Activations Density 0.151%

    No Known Activations