© 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. 20474
    Prev
    Next
    INDEX
    Explanations

    action verb followed by article or possessive

    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
     nowhere
    -0.07
    èĥ½åIJ¦
    -0.06
    åĨįä¸ī
    -0.06
    emps
    -0.06
    pas
    -0.06
     generously
    -0.06
    ahari
    -0.06
    审议éĢļè¿ĩ
    -0.06
    ä¹Ī
    -0.06
     unanimously
    -0.06
    POSITIVE LOGITS
    好åij¢
    0.12
    çļĦåij¢
    0.12
    以åıĬå¦Ĥä½ķ
    0.11
    åıĪä¸į
    0.10
     efficacement
    0.10
     ÙĪÙĥÙĬÙģ
    0.10
    åıĪä¸į失
    0.10
    ä½łåij¢
    0.10
    æľīæķĪåľ°
    0.09
     efficiently
    0.09
    Activations Density 0.722%

    No Known Activations