© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30168
    Prev
    Next
    INDEX
    Explanations

    both or two

    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
    ugat
    -0.08
    ajian
    -0.07
    åij
    -0.07
    ×ķ×Ĺ
    -0.07
    ezen
    -0.06
    oser
    -0.06
    ĩ´
    -0.06
    uien
    -0.06
    ujian
    -0.06
    ianya
    -0.06
    POSITIVE LOGITS
    å°±è¿Ļæł·
    0.09
    æĢ»çļĦæĿ¥è¯´
    0.08
    overall
    0.08
    æĢ»èĢĮè¨Ģä¹ĭ
    0.08
    以ä¸Ĭå°±æĺ¯
    0.08
     together
    0.08
    è¿Ļ两
    0.07
    æĢ»ä¹ĭ
    0.07
    obo
    0.07
    ãģ©ãģ¡ãĤīãĤĤ
    0.07
    Activations Density 0.143%

    No Known Activations