© 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. 11830
    Prev
    Next
    INDEX
    Explanations

    outputting or printing

    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
    èĦļè¸ıå®ŀ
    -0.07
    ä¸ĢåĪĨéĴ±
    -0.07
    -sized
    -0.06
    orr
    -0.06
    ARTH
    -0.06
    ieu
    -0.06
    éķ¿éĢĶ
    -0.06
    åĪĨæī¹
    -0.06
    æĹłä¸Ģ
    -0.06
    ias
    -0.06
    POSITIVE LOGITS
    /print
    0.08
    好åĥıåľ¨
    0.08
    ença
    0.07
     noqa
    0.07
    ilas
    0.07
    ubin
    0.07
    ascade
    0.07
    (Output
    0.07
    latex
    0.07
    uards
    0.07
    Activations Density 0.003%

    No Known Activations