© 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. 56304
    Prev
    Next
    INDEX
    Explanations

    being developed or underway

    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
    ìį¨
    -0.09
    éĩįéĩįçļĦ
    -0.09
    ure
    -0.08
    terer
    -0.07
    ically
    -0.07
     eventual
    -0.07
    vertime
    -0.07
    otin
    -0.07
    órd
    -0.07
    aix
    -0.07
    POSITIVE LOGITS
    æĪĸå°Ĩ
    0.10
    ev
    0.08
    atch
    0.08
    sver
    0.07
    æĢİæł·çļĦ
    0.07
    ulum
    0.07
    ê»ı
    0.07
    dessen
    0.07
    åĴĮæľªæĿ¥
    0.07
    EMENT
    0.07
    Activations Density 0.057%

    No Known Activations