© 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. 26446
    Prev
    Next
    INDEX
    Explanations

    se explica

    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
    customize
    -0.07
    ierung
    -0.07
    æĸĹç½Ĺ
    -0.07
    ående
    -0.07
     δεν
    -0.07
    ized
    -0.07
    å·²
    -0.07
    visor
    -0.07
    ville
    -0.07
    onomia
    -0.06
    POSITIVE LOGITS
    çĦ¶å¤§
    0.07
    ä½ľåģĩ
    0.07
    åĬŁäºİ
    0.07
    çĦ¶æĺ¯
    0.07
    ãģĭãģ®
    0.07
    ähr
    0.07
    æľ¬æĸĩ为åįļ主
    0.07
    æķĻäºİ
    0.07
    ong
    0.07
    zig
    0.07
    Activations Density 0.026%

    No Known Activations