© 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. 21645
    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
    atat
    -0.07
    åıªè¦ģèĥ½
    -0.07
    åľ°æŃ¥
    -0.07
    ank
    -0.07
     kek
    -0.07
    沿
    -0.07
     SUBSTITUTE
    -0.06
    åĪ©äºļ
    -0.06
     <![
    -0.06
    _NUMERIC
    -0.06
    POSITIVE LOGITS
    æľ¬æĿ¥å°±
    0.08
    æĭīå°Ķ
    0.07
    ä¸į欲
    0.07
     heran
    0.06
    人家çļĦ
    0.06
    æīĢ以è¦ģ
    0.06
    adier
    0.06
    اء
    0.06
    avian
    0.06
    arus
    0.06
    Activations Density 0.000%

    No Known Activations