© 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. 27758
    Prev
    Next
    INDEX
    Explanations

    specific numbers and abbreviations

    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
    amme
    -0.09
     perj
    -0.09
    带æĪijåİ»
    -0.08
    <|box_end|>
    -0.08
    ToDevice
    -0.08
     Contras
    -0.08
     мной
    -0.08
    樽
    -0.08
     séqu
    -0.08
     TBD
    -0.08
    POSITIVE LOGITS
    å°Ħ
    0.06
    æĹ©
    0.06
    åī©ä¸ĭ
    0.06
    ly
    0.06
    ×Ļ×¢
    0.06
    upan
    0.05
    次
    0.05
     impending
    0.05
    åħ¬å¼ı
    0.05
     kÄħ
    0.05
    Activations Density 0.001%

    No Known Activations