© 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. 15811
    Prev
    Next
    INDEX
    Explanations

    legal drive partnership women

    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
    å¾Īå¤ļ
    -0.08
    ï½ŀãĢĤ
    -0.07
    ä¸įå°ij
    -0.06
    æīĢæľīçļĦ
    -0.06
    æŶéĹ´æĺ¯
    -0.06
    å¾Īå¤ļåľ°æĸ¹
    -0.06
     ë³´ë©´
    -0.06
    没æľīäºĨ
    -0.06
     ::=
    -0.06
    è¿Ļæĺ¯å¯¹
    -0.06
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.13
    äºİä¸Ģä½ĵçļĦ
    0.13
     "></
    0.11
     }}"></
    0.11
    å·¥ä½ľçļĦéĢļçŁ¥
    0.11
    ])))
    0.10
     /></
    0.10
     }}</
    0.10
    为ä¸Ģä½ĵçļĦ
    0.10
    çļĦæŶåĢĻäºĨ
    0.10
    Activations Density 0.023%

    No Known Activations