© 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. 10847
    Prev
    Next
    INDEX
    Explanations

    relationship between

    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
    ysz
    -0.07
     enc
    -0.07
    æīĭæľºç«¯
    -0.06
    .fe
    -0.06
    ir
    -0.06
    ļĮ
    -0.06
    å°Ĩè¿ĻäºĽ
    -0.06
    wr
    -0.06
    åĢ¦
    -0.06
    就该
    -0.06
    POSITIVE LOGITS
    è¶Ĭæĺ¯
    0.13
    -proxy
    0.09
     ยิà¹Īà¸ĩ
    0.09
    åIJĥäºĨ
    0.09
    è¶ĬæĹ©
    0.09
    è¶Ĭ
    0.08
    ÑİÑĢ
    0.08
     بÙħجرد
    0.08
    ä½ıäºĨ
    0.08
    æĦĪ
    0.08
    Activations Density 0.241%

    No Known Activations