© 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. 55873
    Prev
    Next
    INDEX
    Explanations

    code comments or source code

    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
    ovu
    -0.09
    upu
    -0.09
    åĽłä¸ºæľīäºĨ
    -0.08
    atkan
    -0.08
    ÐļС
    -0.08
    ä¸ĢèģĮ
    -0.08
    à¹Ħร
    -0.08
    çļĦå·¥ä½ľä½ľé£İ
    -0.08
     lục
    -0.08
    à¹Ģà¸ľ
    -0.08
    POSITIVE LOGITS
    å¤ĸçĶ¨
    0.06
     +
    0.06
    çĭłçĭł
    0.06
    æĿŁ
    0.06
    æIJŃ
    0.05
    èĩªçĦ¶
    0.05
    欣
    0.05
    æĥŃæĦ§
    0.05
    åīįèĢħ
    0.05
    ä»ij
    0.05
    Activations Density 0.002%

    No Known Activations