© 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. 38610
    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
    åį§
    -0.07
    é¦ı
    -0.07
    sta
    -0.07
    emen
    -0.07
    plib
    -0.06
    åħ»é¢ľ
    -0.06
    CTest
    -0.06
    essen
    -0.06
    éļIJéļIJ
    -0.06
    iere
    -0.06
    POSITIVE LOGITS
    è¿ĻäºĽåĽłç´ł
    0.08
    æķħ人
    0.08
     relationships
    0.08
     Relationships
    0.08
    abda
    0.08
    æľīæĥħ
    0.08
    ıb
    0.08
    繫
    0.08
    å¯Ĩå¸ĥ
    0.08
    æѤçĶŁ
    0.08
    Activations Density 0.000%

    No Known Activations