© 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. 41254
    Prev
    Next
    INDEX
    Explanations

    Party, deal, Pen, Character, rail

    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
    pick
    -0.06
     Maid
    -0.06
    è¿Ļæł·çļĦéĹ®é¢ĺ
    -0.06
    auff
    -0.06
    ä¹°çļĦ
    -0.06
    Ùĭ
    -0.05
     pensi
    -0.05
    è¢Ń
    -0.05
    mh
    -0.05
    à§įষ
    -0.05
    POSITIVE LOGITS
    grafer
    0.07
    auge
    0.07
    <strong
    0.07
    åįģäºĮæĮĩ
    0.07
    بÙĤ
    0.07
    åIJĮå±ħ
    0.07
    rlen
    0.07
    णा
    0.07
    burgh
    0.07
    CEF
    0.07
    Activations Density 0.075%

    No Known Activations