© 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. 48544
    Prev
    Next
    INDEX
    Explanations

    programming verbs

    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
    å¿ħä¸įåı¯
    -0.07
     galima
    -0.07
    说ä¸įå®ļ
    -0.07
     schien
    -0.07
    å®ŀå±ŀ
    -0.07
    åĴ±ä»¬
    -0.06
    çļĦæĪij
    -0.06
    æĪijå·²
    -0.06
    alia
    -0.06
    å°½åľ¨
    -0.06
    POSITIVE LOGITS
     ourselves
    0.09
     accordingly
    0.08
     Ø£ÙĪÙĦاÙĭ
    0.08
    elah
    0.08
    èĻ
    0.08
    åīįåħĪ
    0.07
    ymous
    0.07
    akens
    0.07
    水份
    0.07
    ihn
    0.07
    Activations Density 0.127%

    No Known Activations