© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32892
    Prev
    Next
    INDEX
    Explanations

    .pl

    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
    è·¯éĢı
    -0.07
    å°ĨçIJĥ
    -0.07
    åı¯ä»¥æľīæķĪåľ°
    -0.06
    åľ¨å¾Ī大ç¨ĭ度ä¸Ĭ
    -0.06
    åħĭæĸ¯
    -0.06
    æŃ£æĺ¯åľ¨
    -0.06
    çİĩåĴĮ
    -0.06
    åIJİåį³åı¯
    -0.06
    ä½łè¿ĺåı¯ä»¥
    -0.06
     sound
    -0.06
    POSITIVE LOGITS
    çİ¥
    0.07
    bower
    0.07
    alum
    0.07
    ãĥ¬ãĤ¹ãĥĪ
    0.07
    ħ
    0.07
    bdb
    0.07
    ä¸ĭåIJĮ
    0.07
    );$
    0.07
    bv
    0.07
     overe
    0.07
    Activations Density 0.004%

    No Known Activations