© 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. 11575
    Prev
    Next
    INDEX
    Explanations

    review, discusses, presents, or describes

    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
    /or
    -0.07
    ä½łè¯´çļĦ
    -0.07
    åħ·ä½ĵå¦Ĥä¸ĭ
    -0.07
    ä»ĸçļĦä½ľåĵģ
    -0.06
    以ä¸ĭæĿ¡ä»¶
    -0.06
    解åĨ³è¿Ļ个éĹ®é¢ĺ
    -0.06
    ä¸Ĭä¸ĢæĿ¡
    -0.06
    æĪij们è¿ĻäºĽ
    -0.06
    ãģ¨ãģ®ãģĵãģ¨
    -0.06
    èĩ³å°ij
    -0.06
    POSITIVE LOGITS
     discusses
    0.10
    éĺIJè¿°äºĨ
    0.10
    åĪĨæŀIJäºĨ
    0.09
    讨论äºĨ
    0.09
    讨
    0.09
     briefly
    0.08
    ä»ĭç»įäºĨ
    0.08
     discussion
    0.08
    讨论
    0.08
    æݢ讨äºĨ
    0.08
    Activations Density 0.375%

    No Known Activations