© 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. 21540
    Prev
    Next
    INDEX
    Explanations

    proper noun possessives

    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
    éĩįçĤ¹æĺ¯
    -0.08
    åĥıæĺ¯
    -0.08
    rcode
    -0.08
    缸åħ³æĥħåĨµ
    -0.08
    æīĢæľīçļĦ
    -0.07
    ëĭ¹ìĿĢ
    -0.07
    æľĢéĩįè¦ģçļĦæĺ¯
    -0.07
    çļĦè¿ĺæľī
    -0.07
    ái
    -0.07
    å·¥ä½ľæĺ¯
    -0.07
    POSITIVE LOGITS
    çļĦä¸Ģç§į
    0.14
    çļĦéĩįè¦ģç»ĦæĪIJéĥ¨åĪĨ
    0.12
    å·¥ä½ľçļĦéĩįè¦ģ
    0.11
    çļĦéĩįè¦ģä¾Ŀæį®
    0.11
    çļĦä¸Ģ个
    0.11
    çļĦä¸Ģéĥ¨åĪĨ
    0.11
    çļĦä¸Ģ个éĩįè¦ģ
    0.10
    çļĦä¸Ģ種
    0.10
    ä¸ŃçļĦä¸Ģç§į
    0.10
    çļĦä¸Ģéģĵ
    0.10
    Activations Density 0.029%

    No Known Activations