© 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. 11851
    Prev
    Next
    INDEX
    Explanations

    should be followed by a verb

    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
     شدÙĨ
    -0.07
    椿
    -0.07
    burgo
    -0.07
     devoir
    -0.07
     nowhere
    -0.06
    çļĦä¸Ģ段
    -0.06
    åĴĮä¸Ń
    -0.06
    .icons
    -0.06
    .fs
    -0.06
    缸继
    -0.06
    POSITIVE LOGITS
    emy
    0.08
    æĺİäºĨ
    0.07
    çħĮ
    0.07
    ãĥİãĤ¦
    0.07
    kke
    0.07
    بÙĩ
    0.07
    ìĸij
    0.06
    æĺİ
    0.06
    anza
    0.06
    æĹ¢
    0.06
    Activations Density 0.020%

    No Known Activations