© 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. 49260
    Prev
    Next
    INDEX
    Explanations

    example or eg

    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
    neau
    -0.09
    èĢĮä¸Ķè¿ĺæĺ¯
    -0.08
    sdk
    -0.08
    cule
    -0.08
    ®
    -0.08
    ä¹Łè®ĵ
    -0.08
    ór
    -0.08
    eren
    -0.07
    ç»ĻäºĨæĪij们
    -0.07
    ä¹Łå°±æĦıåij³çĿĢ
    -0.07
    POSITIVE LOGITS
    atively
    0.07
    à¹Ģà¸Ķียว
    0.07
     dụ
    0.07
    说æĺİ
    0.07
     various
    0.07
    appropri
    0.07
    ä¸Ģæĸij
    0.07
    upati
    0.07
    igator
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
    Activations Density 0.002%

    No Known Activations