© 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. 14921
    Prev
    Next
    INDEX
    Explanations

    but that's

    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
    ัà¸Ķ
    -0.07
    ä¼łä¸ĸ
    -0.07
    å®ŀå¿ĥ
    -0.07
    ÙĩÛĮ
    -0.07
    hs
    -0.07
    gor
    -0.07
    æľŁæ»¡
    -0.07
    åį´åıĪ
    -0.06
    åį´ä¸į
    -0.06
    æĦŁè¨Ģ
    -0.06
    POSITIVE LOGITS
    å¾Īä¹ħ
    0.10
    太ä¹ħ
    0.09
    aned
    0.09
    趣
    0.07
    alous
    0.07
    aruan
    0.07
    宿
    0.07
    agog
    0.07
     *}
    0.07
    adari
    0.07
    Activations Density 0.038%

    No Known Activations