© 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. 62904
    Prev
    Next
    INDEX
    Explanations

    door hardware and mechanisms

    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
     pipeline
    -0.07
     saturated
    -0.07
    pipeline
    -0.07
    å¤ĩ课
    -0.06
    纱å¸ĥ
    -0.06
     Pipeline
    -0.06
    饱åĴĮ
    -0.06
    Pipeline
    -0.06
    头æĪ´
    -0.06
    æ±Ĥ羣
    -0.06
    POSITIVE LOGITS
     doors
    0.10
     hinges
    0.09
     door
    0.09
     оÑĤкÑĢ
    0.09
    -opening
    0.09
    å¼ĢåIJ¯
    0.09
    çļĦéŨ
    0.09
    éŨç¦ģ
    0.09
    abin
    0.09
    éĸĢ
    0.09
    Activations Density 0.240%

    No Known Activations