© 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. 13992
    Prev
    Next
    INDEX
    Explanations

    gets over, will be, may be

    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
    çī¹æľī
    -0.10
    zinho
    -0.09
    whose
    -0.09
    åıijå±ķæĸ°
    -0.08
    æĢ§èĥ½å¥½
    -0.08
    ä»ħä½ľ
    -0.08
    æľīè¾ĥ强çļĦ
    -0.08
    å¾Īéķ¿çļĦ
    -0.08
    æĤ´
    -0.08
     cuya
    -0.08
    POSITIVE LOGITS
    åıijçĶŁåıĺåĮĸ
    0.07
     stimmen
    0.07
    åĴĮ产åĵģ
    0.07
    æĺ¯å¤ļå°ij
    0.07
    å®ļæł¼
    0.06
    åĴĮæĬķèµĦ
    0.06
    æ°ı
    0.06
     outweigh
    0.06
    é¢łåĢĴ
    0.06
    åıijçĶŁäºĨåıĺåĮĸ
    0.06
    Activations Density 0.384%

    No Known Activations