© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 9636
    Prev
    Next
    INDEX
    Explanations

    ANNs

    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
    ìĿĺ
    -0.29
    ãģ®
    -0.27
    çļĦ
    -0.25
    çļĦå°±æĺ¯
    -0.23
    çļĦæł¸å¿ĥ
    -0.19
    çļĦå¤ļ
    -0.19
    çļĦè¿ĩç¨ĭä¸Ń
    -0.18
    çļĦåIJĮæĹ¶
    -0.18
    çļĦ两
    -0.18
    çļĦè§Ĵ度
    -0.18
    POSITIVE LOGITS
    çļĦä¸Ģèά
    0.11
    çļĦ人们
    0.10
    çļĦ人工
    0.10
    çļĦ人æķ°
    0.10
    çļĦä¸ĢåĪĩ
    0.10
    çļĦ人éĻħ
    0.10
    çļĦ人åijĺ
    0.10
    çļĦäººæł¼
    0.10
    çļĦä¸Ģèĩ´
    0.10
    çļĦ人群
    0.10
    Activations Density 0.377%

    No Known Activations