© 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. 49739
    Prev
    Next
    INDEX
    Explanations

    is connecting words

    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
    usercontent
    -0.08
     themselves
    -0.07
    ToOne
    -0.07
    åĽ´
    -0.06
    è¿ĩä¸Ģ次
    -0.06
    ä»»æĢ§
    -0.06
    å¾·åįİ
    -0.06
    uman
    -0.06
    IMP
    -0.06
    ihan
    -0.06
    POSITIVE LOGITS
    -invalid
    0.08
    å·¥ä½ľçļĦåIJĮæŶ
    0.07
     answer
    0.07
    ä¸įèĥ½ä½ľä¸º
    0.07
    æľīéĹ®é¢ĺ
    0.07
     CURLOPT
    0.07
     íĭĢ
    0.07
     incorrect
    0.07
    åı¯ä»¥ä½ľä¸º
    0.07
    天å¸Ŀ
    0.07
    Activations Density 0.003%

    No Known Activations