© 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. 49203
    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
    éĿŀ常éĩįè¦ģ
    -0.07
    éĿŀ常éĩįè¦ģçļĦ
    -0.07
    åĨī
    -0.06
    åĩºäºİ
    -0.06
    åħ·æľīéĩįè¦ģçļĦ
    -0.06
    ä¸ĢèĪ¬
    -0.06
    clar
    -0.06
     конкÑĢеÑĤной
    -0.06
    èĬ·
    -0.06
     Ñĥб
    -0.06
    POSITIVE LOGITS
    人åĽŀå¤į
    0.09
    è¿ĺæľī个
    0.09
    ipline
    0.08
    éĢŁåº¦ä¸İ
    0.08
    åĢ¼åıĭ
    0.08
    rene
    0.08
    -stream
    0.07
    é«ĺéĢŁä¸ĭè½½
    0.07
    èİ·è¯Ħ
    0.07
    æĥŁæľī
    0.07
    Activations Density 0.000%

    No Known Activations