© 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. 30195
    Prev
    Next
    INDEX
    Explanations

    solid wood furniture

    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
    轻微çļĦ
    -0.09
    轻微
    -0.08
    å·§å¦Ļ
    -0.08
    åĩıè½»äºĨ
    -0.08
    继ç»Ń沿
    -0.08
    å·§å¦Ļåľ°
    -0.08
    æĽ¿ä»ĸ
    -0.07
    åĩıè½»
    -0.07
    轻度
    -0.07
    ä¹Łä¸įéľĢè¦ģ
    -0.07
    POSITIVE LOGITS
    羣æŃ£çļĦ
    0.14
    羣å®ŀçļĦ
    0.13
    æīįæĺ¯çľŁæŃ£çļĦ
    0.13
    èĢĮä¸įæĺ¯
    0.13
     genuine
    0.12
    çļĦ羣å®ŀ
    0.12
    èĢĮéĿŀ
    0.12
    è¿Ļæīįæĺ¯
    0.12
    羣å®ŀ
    0.12
    羣æŃ£
    0.11
    Activations Density 0.433%

    No Known Activations