© 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. 30152
    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
    riez
    -0.09
    翼翼
    -0.09
    她表示
    -0.09
    çī¹åĪ«å£°æĺİ
    -0.09
    ysh
    -0.08
    obie
    -0.08
     Politique
    -0.08
    æĭŃ缮
    -0.08
    óta
    -0.08
    èĤĦ
    -0.08
    POSITIVE LOGITS
    æĻ®éĢļ
    0.06
     sor
    0.06
    RTL
    0.06
    èĤ²
    0.06
    é£ŀæī¬
    0.06
     prose
    0.06
    åıĻ
    0.06
    æµģçķħ
    0.06
    æĬĴ
    0.06
    ç£
    0.06
    Activations Density 0.000%

    No Known Activations