© 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. 58639
    Prev
    Next
    INDEX
    Explanations

    code and unique identifiers

    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
    æĺ¯ä¸Ģ个人
    -0.07
    å±ķçİ°
    -0.06
    ols
    -0.06
    _except
    -0.06
    åŀ£
    -0.06
    红èī²çļĦ
    -0.06
    ãģ¿ãģ®
    -0.06
    ev
    -0.06
    身åIJİçļĦ
    -0.06
    ubin
    -0.06
    POSITIVE LOGITS
     terb
    0.08
    ancam
    0.07
    cze
    0.07
    ä»»åĬ³
    0.07
     entgegen
    0.07
    ä¹ħä¹ĭ
    0.07
     adelant
    0.07
    astia
    0.07
    ayet
    0.07
    èĪªæ¯į
    0.07
    Activations Density 0.012%

    No Known Activations