© 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. 62441
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tdown
    -0.08
    nay
    -0.07
     ná»ģn
    -0.07
     jad
    -0.07
    åľ¨äºĨåľ°ä¸Ĭ
    -0.07
    -org
    -0.07
     verlie
    -0.07
    ä¸ĭæĿ¥äºĨ
    -0.07
    rophe
    -0.07
    tian
    -0.07
    POSITIVE LOGITS
    èļĬåŃIJ
    0.08
    IGA
    0.07
    quette
    0.07
     lagun
    0.07
    æķĪåºĶ
    0.07
    æľīæķĪ
    0.07
    è·¨
    0.06
    ç²¾ç¥ŀ
    0.06
    Õ¦
    0.06
    DSA
    0.06
    Activations Density 0.000%

    No Known Activations