© 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. 17541
    Prev
    Next
    INDEX
    Explanations

    excerpt-free zone

    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
    好åĥı
    -0.07
    没说
    -0.07
    è¦ģ使
    -0.07
    çıĤ
    -0.07
    .Collection
    -0.07
    “And
    -0.07
    ogram
    -0.07
    使ãģĦ
    -0.06
    rier
    -0.06
    åIJ¬è¯´è¿ĩ
    -0.06
    POSITIVE LOGITS
    å®ŀåľ¨
    0.09
    è¿Ļç§įæĥħåĨµä¸ĭ
    0.08
    å®ŀåľ¨æĺ¯
    0.08
    å¯¦åľ¨
    0.07
     Seriously
    0.07
     seriously
    0.07
    为åİŁåĪĻ
    0.07
    abstract
    0.07
    agod
    0.07
    Seriously
    0.07
    Activations Density 0.045%

    No Known Activations