© 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. 40116
    Prev
    Next
    INDEX
    Explanations

    'Matter of' followed by citation

    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
    iran
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    enges
    -0.07
    主
    -0.07
     innoc
    -0.07
    赶åĪ°
    -0.06
     union
    -0.06
    ingu
    -0.06
    æĤ¨çļĦè¯Ħ论
    -0.06
    iso
    -0.06
    POSITIVE LOGITS
    idr
    0.08
    idt
    0.07
    /plain
    0.07
    æĪ¿å®¢
    0.07
    èij«
    0.07
    /mit
    0.07
    åŁ¹ä¼ĺ
    0.07
    skr
    0.07
    å¡
    0.06
    å²IJ
    0.06
    Activations Density 0.001%

    No Known Activations