© 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. 10504
    Prev
    Next
    INDEX
    Explanations

    senate, department, opinion, before

    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
    éģĹ
    -0.07
    æĿ¡
    -0.07
    êu
    -0.07
    è±
    -0.07
    Äģv
    -0.06
    ãĥIJãĥ¼
    -0.06
    çŃĶé¢ĺåį¡
    -0.06
    稿件æĿ¥æºIJ
    -0.06
    <tbody
    -0.06
     Tonight
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.08
    supports
    0.08
    åıªè¦ģä¸Ģ
    0.07
    è´¥
    0.07
    italia
    0.07
    nger
    0.07
    azu
    0.07
    å±ķå¼Ģåħ¨æĸĩ
    0.07
    æľĢæĸ°èµĦ讯
    0.07
    æĸ°è§Ħå®ļ
    0.07
    Activations Density 0.012%

    No Known Activations