© 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
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60477
    Prev
    Next
    INDEX
    Explanations

    each term or scan

    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
    avan
    -0.08
    oft
    -0.08
    -between
    -0.08
    没æľīåħ¶ä»ĸ
    -0.07
    acco
    -0.07
     certain
    -0.07
     amongst
    -0.07
    æŁIJäºĽ
    -0.07
     междÑĥ
    -0.07
    以ä¸ĬçļĦ
    -0.07
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.08
    alis
    0.08
    }):
    0.08
    )):
    0.07
    éĢIJä¸Ģ
    0.07
    åĪĨæŀIJä¸Ģä¸ĭ
    0.07
    ä¸įåIJĮç¨ĭ度
    0.07
    ê°ģ
    0.07
    æ³ķå¾ĭåĴĮ
    0.07
    ç»ı审çIJĨæŁ¥æĺİ
    0.07
    Activations Density 0.001%

    No Known Activations