© 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. 63446
    Prev
    Next
    INDEX
    Explanations

    directions and speed

    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
    è¿ĩ渡
    -0.08
    ç°ĩ
    -0.08
     transitional
    -0.08
    ä¸ī代
    -0.08
    ikka
    -0.07
    schau
    -0.07
    éĢı
    -0.07
    å±Ĥå±Ĥ
    -0.07
    æµģåħ¥
    -0.07
    åĸľè®¯
    -0.07
    POSITIVE LOGITS
    éĢŁåº¦
    0.11
    éĢŁåº¦åĴĮ
    0.10
     speed
    0.10
     faster
    0.10
    æľĢå¿«
    0.10
    åĮĢéĢŁ
    0.10
     fastest
    0.09
     slower
    0.09
    çļĦéĢŁåº¦
    0.09
    éĢŁåº¦ä¸İ
    0.09
    Activations Density 0.002%

    No Known Activations