© 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. 12248
    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
    èĮ§
    -0.07
    æµģ失
    -0.07
    isma
    -0.07
    ós
    -0.07
    ocker
    -0.06
    theit
    -0.06
    åĨįæİ¥
    -0.06
    иÑģÑĤо
    -0.06
    ëıĪ
    -0.06
     tertinggi
    -0.06
    POSITIVE LOGITS
    eliers
    0.09
    _gps
    0.08
    å¥ij
    0.08
    è¯Ī
    0.07
    Ø´ÙĤ
    0.07
    ä¸Ģ个好çļĦ
    0.07
    çĶ¨å¥½
    0.07
    è°ĥçłĶåijĺ
    0.07
    转载请注æĺİ
    0.07
    æĭīæĸ¯
    0.07
    Activations Density 0.000%

    No Known Activations