© 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. 50051
    Prev
    Next
    INDEX
    Explanations

    sequential stages separation

    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
    èĥ½åĬ¨
    -0.09
    ãĤ¨ãĥ¼ãĤ¸ãĤ§ãĥ³ãĥĪ
    -0.07
    alex
    -0.07
     Helf
    -0.07
    ä»Ģä¹Īéĥ½æ²¡
    -0.07
    æ¹ĥ
    -0.07
    ÐķÐĻ
    -0.07
    ilater
    -0.07
     hydrat
    -0.07
    RIES
    -0.07
    POSITIVE LOGITS
    åĴĮ第äºĮ
    0.11
    çļĦ第äºĮ
    0.09
     successive
    0.09
    åĴĮ第
    0.08
     sequential
    0.08
    sequential
    0.08
    第äºĮ
    0.08
    第äºĮ个
    0.08
     separation
    0.07
     stages
    0.07
    Activations Density 0.007%

    No Known Activations