© 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. 40606
    Prev
    Next
    INDEX
    Explanations

    Greek letters and physics terms

    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
    士åįĴ
    -0.07
    éĤĥ
    -0.07
    åıijå±ķæĶ¹éĿ©å§Ķ
    -0.07
    ä¸Ģ缴ä¿ĿæĮģ
    -0.07
    åħ»æ´»
    -0.07
    å¥ijç¨İ
    -0.07
    èĬĬ
    -0.07
    oop
    -0.07
    èĬ±æľ¨
    -0.06
    Aura
    -0.06
    POSITIVE LOGITS
    ä¸īç±»
    0.08
    人身
    0.08
    ä¸īä¸Ń
    0.08
    lod
    0.08
    ç²ĴåŃIJ
    0.07
     consisted
    0.07
     consists
    0.07
    пÑĢавка
    0.07
     consisting
    0.07
    RDD
    0.07
    Activations Density 0.003%

    No Known Activations