© 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. 61935
    Prev
    Next
    INDEX
    Explanations

    treatment and strategies

    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
    gram
    -0.07
    Gram
    -0.07
     Gram
    -0.07
     unnoticed
    -0.07
     flattering
    -0.07
    çĤĬ
    -0.07
     gram
    -0.06
    å¦ĩ产åĮ»éĻ¢
    -0.06
    æĬķå½±
    -0.06
    lant
    -0.06
    POSITIVE LOGITS
    å¤ĦçIJĨåIJİ
    0.12
    解åĨ³éĹ®é¢ĺçļĦ
    0.11
    åıĬæŶå¤ĦçIJĨ
    0.11
    å¤ĦçIJĨæĸ¹å¼ı
    0.11
    çļĦå¤ĦçIJĨ
    0.11
    解åĨ³éĹ®é¢ĺ
    0.11
    åĮĸå¤ĦçIJĨ
    0.10
    å¤ĦçIJĨ
    0.10
    å¤ĦçIJĨçļĦ
    0.10
    å¤Ħç½®
    0.10
    Activations Density 0.317%

    No Known Activations