© 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. 32983
    Prev
    Next
    INDEX
    Explanations

    professionals with expertise

    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
    á»ĵ
    -0.09
    ppy
    -0.09
    piry
    -0.08
    åĭĩ士
    -0.08
    åĴ¬çīĻ
    -0.08
    ermen
    -0.08
    æ°´åĻ¨
    -0.08
    å¤ļè°¢
    -0.08
    è¹Ī
    -0.08
    	logging
    -0.08
    POSITIVE LOGITS
     expert
    0.11
     expertise
    0.10
    ä¸ĵ家
    0.10
     experts
    0.09
    expert
    0.08
     Expert
    0.08
     advise
    0.08
    ç»ıéªĮ丰å¯ĮçļĦ
    0.07
     cas
    0.07
     specializing
    0.07
    Activations Density 0.476%

    No Known Activations