© 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. 4647
    Prev
    Next
    INDEX
    Explanations

    documentation and tutorials

    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
    æĪij们æĬĬ
    -0.07
    ETCH
    -0.07
    轻轻
    -0.06
    æĥľ
    -0.06
     Leid
    -0.06
    好æŃ¹
    -0.06
    ä¸įæĮī
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    è§Ħæł¼
    -0.06
    itin
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸įåı¯èĥ½çļĦ
    0.16
    并ä¸į容æĺĵ
    0.16
    æĺ¯å¾Īéļ¾
    0.14
    å¾Īéļ¾
    0.13
    éļ¾åº¦å¤§
    0.13
    ä¹Łå¾Īéļ¾
    0.12
     невозможно
    0.12
    éļ¾åº¦
    0.12
     Ñģложно
    0.12
    æĺ¯ä¸įåı¯èĥ½
    0.12
    Activations Density 0.332%

    No Known Activations