© 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. 47399
    Prev
    Next
    INDEX
    Explanations

    providing, protection, storage, improve, detect

    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
    èĢĮèµ°
    -0.07
    人å±ħ
    -0.07
     foc
    -0.07
    åıĸå¾Ĺå®ŀæķĪ
    -0.07
    è¦ģä¹Ī
    -0.07
    人大
    -0.07
    æ²¹çĽIJ
    -0.07
    没æľīåľ¨
    -0.07
    ä¸įä»İ
    -0.07
    Dependencies
    -0.07
    POSITIVE LOGITS
    è¿ĺèĥ½
    0.08
    è¿ĺæıIJä¾Ľ
    0.08
    è¿ĺåı¯
    0.08
    éĤĦèĥ½
    0.08
    è¿ĺ为
    0.08
    è¿ĺåı¯ä»¥
    0.08
    è¿ĺèĥ½å¤Ł
    0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
     providing
    0.07
    æĬµå¾¡
    0.07
    Activations Density 0.237%

    No Known Activations