© 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. 8097
    Prev
    Next
    INDEX
    Explanations

    advertisements and postings

    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¸ĭè½½æĬ¥åijĬ
    -0.08
    opyright
    -0.08
    ÙĪØ·
    -0.08
     Chev
    -0.08
    çªĴ
    -0.07
    ä¿Ŀ驾
    -0.07
    ocks
    -0.07
    åĪĨ享åĨħ容
    -0.07
    	Copyright
    -0.07
     imports
    -0.07
    POSITIVE LOGITS
     attracting
    0.12
    åijĬ示
    0.12
    å¼ĢæĶ¾
    0.12
     inviting
    0.11
    åħ¬åijĬ
    0.11
     posted
    0.11
    æĭĽåĭŁ
    0.11
    åĭŁéĽĨ
    0.11
     attract
    0.11
    æĭĽ
    0.11
    Activations Density 0.481%

    No Known Activations