© 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. 7744
    Prev
    Next
    INDEX
    Explanations

    boundary conditions

    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
    ä¿ĿæĬ¤å¥½
    -0.07
    кл
    -0.07
    ooth
    -0.07
    ä»Ļ
    -0.06
    orrect
    -0.06
     protected
    -0.06
    åĬ¨äºº
    -0.06
    å¦ĤæĤ¨
    -0.06
     Moy
    -0.06
     ours
    -0.06
    POSITIVE LOGITS
     ìļ©
    0.07
    绣称
    0.07
     offseason
    0.07
    åĬłå¼ºåŃ¦ä¹ł
    0.07
    åıĺéĩı
    0.07
    æķ´åIJĪ
    0.07
    regor
    0.07
    าะ
    0.07
    ìļ©
    0.07
    combined
    0.07
    Activations Density 0.003%

    No Known Activations