© 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. 29090
    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
    hammer
    -0.07
    çļĦç¡®
    -0.07
    oslav
    -0.06
    ħ
    -0.06
    çļĦè¦ģ
    -0.06
    æŀ¶åŃIJ
    -0.06
     *
    -0.06
    ank
    -0.06
    åĩºè®©
    -0.06
    unes
    -0.06
    POSITIVE LOGITS
    éĿĪ
    0.08
    íĥķ
    0.08
    amanan
    0.07
    æ³ķç½ij
    0.07
    lli
    0.07
     dever
    0.07
    建平
    0.07
    achu
    0.07
    à¸Ńาร
    0.07
    lx
    0.07
    Activations Density 0.000%

    No Known Activations