© 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. 47159
    Prev
    Next
    INDEX
    Explanations

    david-weill

    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
    ...
    -0.06
     crypt
    -0.06
    äºijä¸Ń
    -0.06
    å«Į
    -0.06
    å®Ľ
    -0.06
    ives
    -0.06
     config
    -0.06
    Config
    -0.05
     Fre
    -0.05
     (
    -0.05
    POSITIVE LOGITS
    £¼
    0.09
    orza
    0.09
    åĮ¹éħįçļĦ
    0.09
    ä¹Łåı¯ä»¥çĶ¨
    0.09
    è¿ĺæľīä¸Ģç§į
    0.08
    egan
    0.08
    çļĦè¿ĺæľī
    0.08
    åı¦å¤ĸä¸Ģç§į
    0.08
    /animate
    0.08
    åįĬåĬŁ
    0.08
    Activations Density 0.018%

    No Known Activations