© 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. 19720
    Prev
    Next
    INDEX
    Explanations

    currency units and conversions

    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
    editable
    -0.08
     Moff
    -0.07
    ä¼łçļĦ
    -0.07
    å°½åı¯èĥ½åľ°
    -0.07
    æĿĥçļĦ
    -0.07
    è®¤çľŁåģļ好
    -0.06
    åķĨåĬ¡åĮº
    -0.06
    ä¸įèĻļ
    -0.06
    åħĭéļ¾
    -0.06
    anko
    -0.06
    POSITIVE LOGITS
    vere
    0.07
    æķ¢
    0.07
    erra
    0.07
    amanya
    0.07
    à¸Ńาย
    0.07
    -txt
    0.07
    _den
    0.07
    hent
    0.07
    æīį对
    0.07
    som
    0.07
    Activations Density 0.004%

    No Known Activations