© 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. 30560
    Prev
    Next
    INDEX
    Explanations

    circulated ads, induced, licking lips

    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
    æĸ°åĬłåĿ¡
    -0.09
    vsp
    -0.07
    çĻ¾è®¡
    -0.07
    ÑģÑĤави
    -0.07
    æĸĩç«łäºĨ
    -0.07
    hez
    -0.07
    Õ©
    -0.07
    åħ¶å®ĥçļĦ
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    lico
    -0.07
    POSITIVE LOGITS
    çļĦæĺ¯
    0.15
    çļĦæĺ¯ä¸Ģ个
    0.14
    çļĦæĺ¯ä»Ģä¹Ī
    0.12
    çļĦçī¹çĤ¹æĺ¯
    0.11
    æĥ¯äºĨ
    0.11
    çļĦå°±æĺ¯
    0.11
    åģļçļĦå°±æĺ¯
    0.11
    çļĦä½ľçĶ¨æĺ¯
    0.10
    æŶä¼ļ
    0.10
    è¿ĩçļĦ
    0.09
    Activations Density 0.018%

    No Known Activations