© 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. 12346
    Prev
    Next
    INDEX
    Explanations

    law school

    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
    verket
    -0.07
    ledge
    -0.07
    æľīåħ³äºİ
    -0.07
    leck
    -0.07
    gang
    -0.07
    wier
    -0.06
    plier
    -0.06
     exac
    -0.06
    باÙĨ
    -0.06
    ož
    -0.06
    POSITIVE LOGITS
    ä¹ĭ为
    0.06
     SetLastError
    0.06
     lá»Ļi
    0.06
    å°±è¿Ļä¹Ī
    0.06
    ä½ľä¸ºä¸Ģ项
    0.06
     appunto
    0.06
    ãģķãģ¾
    0.06
    mania
    0.06
    odon
    0.06
    opodob
    0.06
    Activations Density 1.911%

    No Known Activations