© 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. 60292
    Prev
    Next
    INDEX
    Explanations

    namespace System

    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
    æĪijçĪ±
    -0.07
    zi
    -0.07
    usi
    -0.06
    sst
    -0.06
    th
    -0.06
    cks
    -0.06
    åѦåīį
    -0.06
    ught
    -0.06
    {}
    -0.06
    uti
    -0.06
    POSITIVE LOGITS
    ender
    0.07
     Masih
    0.07
    klin
    0.07
    榴
    0.07
    /cop
    0.07
    ecter
    0.07
    çĻ»è®°è¯ģ
    0.07
    æľĢè¿ijæĽ´æĸ°
    0.07
    çī¹èѦ
    0.07
    麵åĮħ
    0.07
    Activations Density 0.003%

    No Known Activations