© 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. 56704
    Prev
    Next
    INDEX
    Explanations

    component parts

    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
     tzv
    -0.10
     tzw
    -0.10
    åĸ»
    -0.09
    возмо
    -0.09
    åįģä½Ļ
    -0.09
     ê°ģì¢ħ
    -0.08
    çļĦåIJĦç±»
    -0.08
    åIJĦç±»
    -0.08
    æѤç§į
    -0.08
     khá»ijng
    -0.08
    POSITIVE LOGITS
    0.13
    0.09
    å¾Īæ£Ĵ
    0.09
    ä¼¼ä¹İæĺ¯
    0.09
    缸å½ĵ大çļĦ
    0.09
    å¼ķ人注
    0.08
    æīĢæľīè¿ĻäºĽ
    0.08
    æĺİæĻº
    0.08
    åĪ°å¤Ħéĥ½æĺ¯
    0.08
    ä¸įæĺ¯åIJĹ
    0.08
    Activations Density 0.123%

    No Known Activations