© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47427
    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
    åĵŃ
    -0.08
    ลาส
    -0.08
    ä¸Ģæĸĩ
    -0.08
     TERM
    -0.07
     Proxy
    -0.07
    å¥Ĺ
    -0.07
    .Term
    -0.07
    izin
    -0.07
    æľ¬æĬ¥
    -0.07
    abeth
    -0.07
    POSITIVE LOGITS
    quet
    0.07
    EE
    0.07
    稽
    0.06
    _ATTRIB
    0.06
    bü
    0.06
    çļĦä¸Ńå¹´
    0.06
    åIJĴ
    0.06
    aire
    0.06
    æĶ¾ä¸Ĭ
    0.06
    æ³ķå¾ĭéĹ®é¢ĺ
    0.06
    Activations Density 0.000%

    No Known Activations