© 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. 38278
    Prev
    Next
    INDEX
    Explanations

    the problem is

    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
    celli
    -0.08
    dma
    -0.08
    aign
    -0.08
    ampir
    -0.08
    imbau
    -0.08
     alguna
    -0.08
    ÙħاÙĥÙĨ
    -0.08
    isas
    -0.08
    ×IJ×ķ
    -0.07
    ayet
    -0.07
    POSITIVE LOGITS
    缺å°ij
    0.09
    åľ¨äºİ
    0.08
    è¿ĻäºĽéĹ®é¢ĺ
    0.08
    缺ä¹ı
    0.08
    ä¸įåľ¨äºİ
    0.07
    å°±åľ¨äºİ
    0.07
    ä¸Ģ个éĹ®é¢ĺ
    0.07
    çļĦéĹ®é¢ĺæĺ¯
    0.07
     insufficient
    0.07
     vex
    0.07
    Activations Density 0.095%

    No Known Activations