© 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. 896
    Prev
    Next
    INDEX
    Explanations

    uncertainty, efficiency, community

    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
    çŃī设å¤ĩ
    -0.08
    .dep
    -0.08
    èijĨ
    -0.08
    folio
    -0.08
    arana
    -0.08
    нибÑĥдÑĮ
    -0.07
    odata
    -0.07
    åѦä½įè¯ģ书
    -0.07
    Ó¯
    -0.07
    ykk
    -0.07
    POSITIVE LOGITS
    åİ»æĥ³
    0.07
    主è¦ģä½ĵçİ°åľ¨
    0.07
    æĬĬäºĭæĥħ
    0.07
    isco
    0.07
    ç²
    0.07
    åIJijåīįèµ°
    0.06
    èį¡
    0.06
    人已
    0.06
    æĹ¢çĦ¶
    0.06
    ä½ĵçİ°åľ¨
    0.06
    Activations Density 0.049%

    No Known Activations