© 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. 17027
    Prev
    Next
    INDEX
    Explanations

    programming languages and code snippets

    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
    起泡
    -0.07
    èµ·
    -0.06
    ãĥ£
    -0.06
    人æ°ijæ³ķéĻ¢
    -0.06
    ãģ¡
    -0.06
    ancellationToken
    -0.06
    çŁŃçļĦ
    -0.06
    abal
    -0.05
    ora
    -0.05
    Å
    -0.05
    POSITIVE LOGITS
    ë°Ķë¡ľ
    0.09
    æķ¬è¯·åħ³æ³¨
    0.09
    itchens
    0.08
    )ãĢį
    0.07
    ">@
    0.07
    ï¼īãĢį
    0.07
    erals
    0.07
    rastructure
    0.07
    immy
    0.07
    tagli
    0.07
    Activations Density 0.273%

    No Known Activations