© 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. 15705
    Prev
    Next
    INDEX
    Explanations

    return statements

    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
    ucher
    -0.07
    å½Ĵæł¹
    -0.07
    rence
    -0.06
    óm
    -0.06
    ogr
    -0.06
    olina
    -0.06
    ollar
    -0.06
    iny
    -0.06
    çļĦä¼ĺåĬ¿
    -0.06
    fø
    -0.06
    POSITIVE LOGITS
    ERRU
    0.07
    arine
    0.07
    arana
    0.07
    athe
    0.07
    clist
    0.07
    atul
    0.07
    uert
    0.07
    ações
    0.07
    arne
    0.07
     quietly
    0.07
    Activations Density 0.006%

    No Known Activations