© 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. 21999
    Prev
    Next
    INDEX
    Explanations

    short answer

    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°±æĺ¯æĪij们çļĦ
    -0.09
    æī©å±ķèµĦæĸĻ
    -0.08
    å®ĥå°±æĺ¯
    -0.08
    اÙĨØ´
    -0.08
    æĹłéĺ»
    -0.07
    åıĪæľīä»Ģä¹Ī
    -0.07
    ewnÄĻ
    -0.07
    ë§IJë¡ľ
    -0.07
    اب
    -0.07
    ä¸įè¿ĩä»ĸ
    -0.07
    POSITIVE LOGITS
    пиÑĤ
    0.06
    ï¼ļ
    0.06
    ılı
    0.06
    mez
    0.06
    æĭĶ
    0.06
    orong
    0.06
    å¾ĭå·±
    0.06
    籤
    0.06
    olders
    0.06
    æ¯Ĺ
    0.05
    Activations Density 0.006%

    No Known Activations