© 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. 20901
    Prev
    Next
    INDEX
    Explanations

    ```the Software```

    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
    ï¼ģï¼ģ
    -0.08
    elaar
    -0.08
     nám
    -0.07
    ostar
    -0.07
    ï¼ģï¼ģï¼ģ
    -0.07
    大éĥ¨ä»½
    -0.07
    æĥħæľī
    -0.07
    èݱæĸ¯
    -0.07
    tribu
    -0.07
    zás
    -0.07
    POSITIVE LOGITS
    ç»ĵ
    0.07
    éĻµ
    0.07
    åįĸ
    0.07
    ect
    0.07
    clang
    0.07
    è¹
    0.06
    posts
    0.06
    .analytics
    0.06
    ç¨
    0.06
    客
    0.06
    Activations Density 1.360%

    No Known Activations