© 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. 27672
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    °
    -0.07
    æľīä½Ļ
    -0.06
    åĩºä¸į
    -0.06
    ken
    -0.06
    ilers
    -0.06
    semb
    -0.06
    æĿ¥èĩª
    -0.06
    çĦ¶æĺ¯
    -0.06
    chema
    -0.06
    é¢ĺåIJį
    -0.06
    POSITIVE LOGITS
    upan
    0.10
    úst
    0.08
    æĮĩå¯¼å·¥ä½ľ
    0.08
    å·¥ä½ľçļĦåIJĮæŶ
    0.07
    è¿Ļ个éĹ®é¢ĺçļĦ
    0.07
    baran
    0.07
    pez
    0.07
    çݯå¢ĥä¸İ
    0.07
    æľīåħ³äºĭ项
    0.07
    çIJĨ论ä¸İå®ŀè·µ
    0.07
    Activations Density 0.001%

    No Known Activations