© 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. 3369
    Prev
    Next
    INDEX
    Explanations

    began with, came when, another day

    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
     ourselves
    -0.08
    å¥Īä½ķ
    -0.08
    æĪij们èĩªå·±
    -0.07
    åĴ±ä»¬çļĦ
    -0.07
    å¿«å¿«
    -0.07
     goodies
    -0.07
    è¶ĭåIJij
    -0.07
    å²Ĥä¸įæĺ¯
    -0.07
    بد
    -0.07
    ÐľÐļ
    -0.07
    POSITIVE LOGITS
    _WORDS
    0.07
     à¸Ħรัà¸ļ
    0.06
    има
    0.06
    æ½®
    0.06
    atea
    0.06
    ä»Ģä¹Īéĥ½æ²¡æľī
    0.06
    kou
    0.06
    pread
    0.06
    ħ
    0.06
     Hùng
    0.06
    Activations Density 0.577%

    No Known Activations