© 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. 14269
    Prev
    Next
    INDEX
    Explanations

    first introducing a topic

    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
    æѤæŶ
    -0.08
    åIJĮæĹ¶ä¹Ł
    -0.08
    çļĦæľĢç»Ī
    -0.07
    æѤæŶçļĦ
    -0.07
    æľĢç»Ī
    -0.07
     furthermore
    -0.07
    ä»İèĢĮå½±åĵį
    -0.07
     consequently
    -0.07
    {})
    -0.07
    èĩ³æѤ
    -0.07
    POSITIVE LOGITS
     ÙĪÙĤبÙĦ
    0.12
    åħ¶æ¬¡
    0.11
    çĦ¶åIJİæĺ¯
    0.11
     dulu
    0.10
    æĪij们åħĪ
    0.10
    çĦ¶åIJİéĢļè¿ĩ
    0.09
    åħ¶æ¬¡æĺ¯
    0.09
    çĦ¶åIJİåľ¨
    0.09
    è¦ģåħĪ
    0.08
    é¦ĸåħĪæĺ¯
    0.08
    Activations Density 0.259%

    No Known Activations