© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 65329
    Prev
    Next
    INDEX
    Explanations

    putting it together

    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
    代ãĤıãĤĬãģ«
    -0.09
    ÙĪزÙĩ
    -0.08
    åĪĨç«Ļ
    -0.07
    ä»İåħ¶
    -0.07
    çĦ¶åIJİåĨį
    -0.07
    ç£IJ
    -0.07
    åĪĨå·¦åı³
    -0.07
    ä»İéĤ£
    -0.07
    ç¶ļãģĦãģ¦
    -0.07
    çį
    -0.07
    POSITIVE LOGITS
    综åIJĪ
    0.10
    综
    0.10
    çļĦ综åIJĪ
    0.09
    綾
    0.08
    ç·ıåIJĪ
    0.08
     ì¢ħíķ©
    0.08
    综åIJĪæĢ§
    0.07
    aroo
    0.07
    åľ¨ä¸Ģèµ·
    0.07
    绣ä¸ĢçļĦ
    0.07
    Activations Density 0.015%

    No Known Activations