© 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. 50656
    Prev
    Next
    INDEX
    Explanations

    domains, categories, and aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    isión
    -0.07
    ÃŃfer
    -0.07
    åĪ©äºļ
    -0.07
     revan
    -0.07
    loys
    -0.07
     kolek
    -0.07
    aksin
    -0.07
    urette
    -0.07
    æµĵæµĵ
    -0.07
    çŃī设å¤ĩ
    -0.07
    POSITIVE LOGITS
    åħ¨éĿ¢çļĦ
    0.09
    åħ¨éĿ¢
    0.09
    涵çĽĸ
    0.09
    åĵªäºĽæĸ¹éĿ¢
    0.09
    åįķ项
    0.08
     areas
    0.08
    çļĦåħ¨éĿ¢
    0.08
     aspects
    0.08
    æĸ¹éĿ¢
    0.08
    é¢ĨåŁŁ
    0.08
    Activations Density 0.339%

    No Known Activations