© 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. 48167
    Prev
    Next
    INDEX
    Explanations

    compliance with, evidence that, encountered in

    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»Ģä¹ĪçļĦ
    -0.06
    Ç
    -0.06
    Âł
    -0.06
     "
    -0.06
     «
    -0.06
     sat
    -0.06
     big
    -0.06
    è¿Ļè¾ĪåŃIJ
    -0.06
     vir
    -0.06
    è¿Ļåı«
    -0.06
    POSITIVE LOGITS
    ×ŀף
    0.08
    Weiterlesen
    0.08
    转载èĩ³
    0.08
     connexion
    0.08
    elaar
    0.08
    áĥĶáĥł
    0.08
    æij¸ç´¢
    0.07
     conclusive
    0.07
     agradecer
    0.07
     remarks
    0.07
    Activations Density 0.125%

    No Known Activations