© 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. 61665
    Prev
    Next
    INDEX
    Explanations

    getting paid

    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
    æľįåĬ¡çŃī
    -0.08
    ä½łçŁ¥éģĵåIJĹ
    -0.08
    ارÙĥ
    -0.07
     ведÑĮ
    -0.07
    éļ¾éģĵæĺ¯
    -0.07
    管çIJĨçŃī
    -0.07
     Other
    -0.07
    å¾·æĸ¯
    -0.07
    好åĥıåľ¨
    -0.07
    other
    -0.07
    POSITIVE LOGITS
    è®¤è®¤çľŁ
    0.09
    èĻ½çĦ¶ä¸įæĺ¯
    0.08
    æľ¬æ¥¼
    0.07
    ssia
    0.07
    èĩ³å°ijåľ¨
    0.07
    èĻ½æľī
    0.07
    èIJ¥éĢłä¸Ģ个
    0.07
     notwithstanding
    0.07
    ä¸įæĮ¯
    0.07
    ä»Ħ
    0.07
    Activations Density 0.007%

    No Known Activations