© 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. 48582
    Prev
    Next
    INDEX
    Explanations

    vessel element, nexus, Jenkins Integration, intestinal transplant, labor reform

    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
    丧
    -0.06
    ä¸İæ°´
    -0.06
    ADING
    -0.06
    ä¸İåīį
    -0.06
    -minded
    -0.06
    -reported
    -0.06
    åĪĴ
    -0.06
    ä¹ĭä¸Ģ
    -0.06
    -faced
    -0.06
     nữa
    -0.06
    POSITIVE LOGITS
    两ä¸į误
    0.12
    ä¼ģä¸ļåħ³ç³»
    0.09
    缸ç»ĵåIJĪçļĦ
    0.09
    çļĦåħ³ç³»
    0.08
    缸ç»ĵåIJĪçļĦæĸ¹å¼ı
    0.08
     nexus
    0.08
    缸ç»ĵåIJĪ
    0.08
     combo
    0.08
     Nexus
    0.08
    两çĶ¨
    0.08
    Activations Density 0.143%

    No Known Activations