© 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. 42996
    Prev
    Next
    INDEX
    Explanations

    experimental design and optimization

    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
     lum
    -0.07
    ebel
    -0.07
    éĤ£æ®µ
    -0.07
     lumin
    -0.07
    ürg
    -0.07
     secur
    -0.07
    igur
    -0.07
    é³Ħé±¼
    -0.07
    çµ®
    -0.07
    ahun
    -0.07
    POSITIVE LOGITS
     planned
    0.08
     factorial
    0.08
    å¸ĥç½®
    0.08
     experimental
    0.08
    å®īæİĴ
    0.07
    anager
    0.07
    è¿IJçŃ¹
    0.07
     Experimental
    0.07
    樣
    0.07
    å®īæİĴçļĦ
    0.07
    Activations Density 0.021%

    No Known Activations