© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33107
    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
    åĨ²åĨ²
    -0.08
    اعÙĬ
    -0.08
    .stem
    -0.08
     reflect
    -0.07
    HEST
    -0.07
    éĿ¢åIJij
    -0.07
    hest
    -0.07
    /sources
    -0.07
    èľķ
    -0.07
    æĺ¯ç»Ļ
    -0.07
    POSITIVE LOGITS
    交åıī
    0.08
    advertisement
    0.07
    cross
    0.07
    ãĤ¯ãĥŃãĤ¹
    0.07
    两边
    0.07
    é£İèµ·
    0.07
     swaps
    0.07
    -cross
    0.07
     equality
    0.06
     unequal
    0.06
    Activations Density 0.000%

    No Known Activations