© 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. 26181
    Prev
    Next
    INDEX
    Explanations

    nanostructures and modifications

    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
    éļı
    -0.07
    æĺĤ
    -0.07
    uzzi
    -0.07
     bó
    -0.07
    اØŃ
    -0.07
    åı«éģĵ
    -0.06
    ä¸ĥä¸ĥ
    -0.06
    计
    -0.06
    æłĩ
    -0.06
    ç´łè´¨
    -0.06
    POSITIVE LOGITS
     architectures
    0.10
    ç»ĵæŀĦ设计
    0.09
    æĪĸåĪ©çĶ¨
    0.08
     gezielt
    0.08
    çļĦçŃĸçķ¥
    0.08
     techniques
    0.08
     strategically
    0.08
    æĬĢæľ¯é¢ĨåŁŁ
    0.08
    ä¸Ĭä¸ĭåĬŁå¤«
    0.08
    å·§å¦Ļ
    0.08
    Activations Density 0.071%

    No Known Activations