© 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. 46570
    Prev
    Next
    INDEX
    Explanations

    project definition and planning

    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
    åľ¨æĹ¥å¸¸çĶŁæ´»ä¸Ń
    -0.07
     streak
    -0.07
    çĶŁæ´»ä¸ŃçļĦ
    -0.07
    ucking
    -0.07
    个ä½ĵçļĦ
    -0.07
    åĩłç§ĴéĴŁ
    -0.07
    orry
    -0.06
    åħ¬åı¸åĬ¨æĢģ
    -0.06
    InstanceId
    -0.06
    å®ŀéªĮä¸Ń
    -0.06
    POSITIVE LOGITS
    å·¥æľŁ
    0.12
    ç«ĭ项
    0.12
     upfront
    0.12
     project
    0.11
    交ä»ĺ
    0.11
    çļĦåīįæľŁ
    0.10
     subcontract
    0.10
    åľŁå»º
    0.10
    å®Įå·¥
    0.10
    åĴĮé¡¹çĽ®
    0.10
    Activations Density 0.204%

    No Known Activations