© 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. 17492
    Prev
    Next
    INDEX
    Explanations

    ultrastructural descriptions

    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
    estos
    -0.07
    æ¶Ī
    -0.07
    æĪĸ缺
    -0.07
    ettori
    -0.07
    oland
    -0.07
    没æľīéĤ£ä¹Ī
    -0.07
    åIJĮ为
    -0.07
    isman
    -0.07
     infiltr
    -0.07
     Parch
    -0.07
    POSITIVE LOGITS
    ä¸įå°ijäºİ
    0.11
    æĮĩå®ļ
    0.08
    ãģ§ãģįãĤĮãģ°
    0.07
    å¿ħå¤ĩ
    0.07
    æĮĩå®ļçļĦ
    0.07
     detail
    0.07
    -required
    0.07
     specified
    0.07
    ä¸įå¤ļ
    0.07
    å¿ħå¤ĩçļĦ
    0.07
    Activations Density 0.004%

    No Known Activations