© 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. 30547
    Prev
    Next
    INDEX
    Explanations

    items or credentials

    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
    åĸľæĢĴ
    -0.07
    udp
    -0.07
    èµĦæºIJç½ij
    -0.07
    åIJĥèĤī
    -0.07
    åĪ°å¤´
    -0.07
    æķĻç§ij书
    -0.07
    éŨæĪ·
    -0.07
    ç¬Ķä¸ĭçļĦ
    -0.07
    udeau
    -0.07
    åıijéĢģéĤ®ä»¶
    -0.07
    POSITIVE LOGITS
    æ²īçĶ¸çĶ¸
    0.10
     berisi
    0.09
    éĢĴç»Ļ
    0.08
    è£ħåľ¨
    0.08
    çıįè´µçļĦ
    0.08
     containing
    0.08
    大å°ıçļĦ
    0.08
     diserahkan
    0.07
    æĶ¾åľ¨äºĨ
    0.07
    妥åĸĦä¿Ŀ管
    0.07
    Activations Density 0.241%

    No Known Activations