© 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. 31982
    Prev
    Next
    INDEX
    Explanations

    Silk Road, NAFTA, Keystone XL, Mainline, Spice Routes

    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
    rach
    -0.07
    çĢij
    -0.07
     dissoci
    -0.06
     vac
    -0.06
    æĺ¯æľī
    -0.06
    禾
    -0.06
    å®ŀçİ°èIJ¥ä¸ļæĶ¶åħ¥
    -0.06
    éļ¶å±ŀäºİ
    -0.06
     th
    -0.06
    ìĩł
    -0.06
    POSITIVE LOGITS
    è¿Ļ项
    0.08
    沿线
    0.08
    对象çļĦ
    0.08
    itan
    0.08
    è§ĦåĪĴ纲è¦ģ
    0.07
    çīµ
    0.07
     stimulus
    0.07
    oba
    0.07
    建设ä¸Ń
    0.07
    ä½ľä¸ºä¸Ģ项
    0.07
    Activations Density 0.013%

    No Known Activations