© 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. 12243
    Prev
    Next
    INDEX
    Explanations

    code delimiters and specific names

    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
    ta
    -0.07
    伶
    -0.07
    åĦĴ
    -0.06
    ׳×ķת
    -0.06
    éĢģåİ»
    -0.06
    "."
    -0.06
    ajara
    -0.06
    ucar
    -0.06
    й
    -0.06
    çļ®çļĦ
    -0.06
    POSITIVE LOGITS
    æĪ·
    0.08
    ů
    0.07
    дÑı
    0.07
    agne
    0.07
    ervo
    0.07
     Alem
    0.07
    жели
    0.07
     Viel
    0.07
    è»Į
    0.07
    erged
    0.07
    Activations Density 0.001%

    No Known Activations