© 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. 33031
    Prev
    Next
    INDEX
    Explanations

    LICENSE information

    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
    oft
    -0.07
    ä½Ĩä»İ
    -0.07
    ales
    -0.07
    æĿĤä¹±
    -0.07
    éĤ£ä¹Łæĺ¯
    -0.06
    att
    -0.06
    REEN
    -0.06
    áŀ½
    -0.06
     ata
    -0.06
    -com
    -0.06
    POSITIVE LOGITS
    ÑĦина
    0.07
    iging
    0.07
    æī©å±ķèµĦæĸĻ
    0.07
    ä¸įæĥľ
    0.07
    ä¸į带
    0.07
    ADVERTISEMENT
    0.07
    ä¸ĢæĮ¥
    0.07
    иÑİ
    0.07
    áĢ¬
    0.07
    碼
    0.07
    Activations Density 0.001%

    No Known Activations