© 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. 50634
    Prev
    Next
    INDEX
    Explanations

    an introduction to a topic

    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
    -0.08
    èĢĮä¸įæĺ¯
    -0.07
     (
    -0.06
    ↵
    -0.06
    in
    -0.06
    1
    -0.06
    åħ±æľī
    -0.06
     y
    -0.06
    ï¼Ī
    -0.06
     rather
    -0.06
    POSITIVE LOGITS
     ê·¸ëłĩì§Ģ
    0.09
    缸åħ³éĹ®çŃĶ
    0.09
    æĽ´å¤ļåħ³äºİ
    0.09
    éĺ¿å§Ĩ
    0.09
    å°ĶèĴĻ
    0.09
    å¤ļè§ģäºİ
    0.09
    èīºæľ¯é¦Ĩ
    0.09
     charme
    0.09
    åıĪåĥı
    0.08
    æĽ´éĢĤåIJĪ
    0.08
    Activations Density 0.011%

    No Known Activations