© 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. 11722
    Prev
    Next
    INDEX
    Explanations

    its/their + noun (occurrence, mortality, reasoning, expression, actual, development, nets, functions, turnover, incidence)

    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
    è¿Ļæĺ¯ä¸ª
    -0.08
    åģļä¸ĢäºĽ
    -0.08
    åĩ«
    -0.08
    ä»ĸå°±æĺ¯
    -0.07
    æĥ³åĬŀæ³ķ
    -0.07
    ymp
    -0.07
    önh
    -0.07
    æıIJä¾ĽæĽ´å¥½çļĦ
    -0.07
    Others
    -0.07
    æŁIJ个
    -0.07
    POSITIVE LOGITS
    çī¹çĤ¹æĺ¯
    0.10
    çļĦçī¹çĤ¹æĺ¯
    0.09
    ä¸įä»ħ
    0.09
    åħ³éĶ®åľ¨äºİ
    0.09
    ä¹ĭæīĢ以
    0.08
    ä¸įä»ħåľ¨
    0.08
    oret
    0.08
    贯穿äºİ
    0.08
    缮æłĩæĺ¯
    0.08
    åı¯åĪĨ为
    0.08
    Activations Density 0.021%

    No Known Activations