© 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. 26452
    Prev
    Next
    INDEX
    Explanations

    damages, punishments, death, distress

    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
    ushima
    -0.08
    åħ¨éĿ¢
    -0.06
     full
    -0.06
     fully
    -0.06
     seri
    -0.06
    åħ¨éĥ¨
    -0.06
     Full
    -0.06
    åħ´åĽ½
    -0.06
    è¿Ľè¡Įåħ¨éĿ¢
    -0.06
    稼
    -0.06
    POSITIVE LOGITS
    ড়া
    0.09
    rÃł
    0.09
    yani
    0.09
    çİ®
    0.08
    enic
    0.08
    å±¹
    0.08
    éģ¨
    0.08
    ±
    0.08
    rave
    0.08
    족
    0.08
    Activations Density 0.001%

    No Known Activations