© 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. 41983
    Prev
    Next
    INDEX
    Explanations

    food and drink ingredients

    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
    ä¸įèĭŁ
    -0.08
    orma
    -0.08
    纲è¦ģ
    -0.08
    ä¸į移
    -0.07
    aclass
    -0.07
    ÙĪرد
    -0.07
    __[
    -0.07
    ollapse
    -0.07
    adre
    -0.07
    /tty
    -0.07
    POSITIVE LOGITS
    ï¼īãĢģ
    0.09
    ãĢįãĢģãĢĮ
    0.08
    roz
    0.07
    ãĢįãĢģ
    0.07
    èĮ¹
    0.07
    `,`
    0.07
    Ñĺе
    0.06
    ighton
    0.06
    以èĩ³
    0.06
    æĹ¥æľĪ
    0.06
    Activations Density 0.577%

    No Known Activations