© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7058
    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
    Negative Logits
    åıªè¦ģæľī
    -0.08
     prim
    -0.07
     osv
    -0.07
     Prim
    -0.07
    åıªè¦ģåľ¨
    -0.07
    olg
    -0.07
    APPER
    -0.06
    addon
    -0.06
    åıªè¦ģæĺ¯
    -0.06
    à¹Ĥล
    -0.06
    POSITIVE LOGITS
    طر
    0.08
    æİĴ
    0.08
    iscos
    0.07
    å°Ķå¾·
    0.07
    isco
    0.06
    cci
    0.06
    -definition
    0.06
    utory
    0.06
    å£
    0.06
    sj
    0.06
    Activations Density 0.000%

    No Known Activations