© 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. 15025
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Tav
    -0.08
    ¬ģ
    -0.08
    åĿĩæĿ¥èĩª
    -0.08
    ä½łå¯¹è¿Ļ个åĽŀçŃĶçļĦè¯Ħä»·æĺ¯
    -0.08
    stown
    -0.08
    åIJİèĢħ
    -0.08
    spel
    -0.08
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.07
    åīįèĢħ
    -0.07
    зво
    -0.07
    POSITIVE LOGITS
    hle
    0.07
    说罢
    0.06
    è¿Ļ个
    0.06
    è¿Ļ个女人
    0.06
    auer
    0.06
    è¿Ļå°ıåŃIJ
    0.06
    ichi
    0.06
    ä¸įå®ľ
    0.06
    mania
    0.06
    OK
    0.06
    Activations Density 0.000%

    No Known Activations