© 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. 64139
    Prev
    Next
    INDEX
    Explanations

    Bob, David, fired name

    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
    hong
    -0.08
    qip
    -0.08
    Managed
    -0.08
    azah
    -0.07
    ekor
    -0.07
    squeeze
    -0.07
    大æĥĬ
    -0.07
     ing
    -0.07
    æĮ¤
    -0.07
    è¹Ń
    -0.07
    POSITIVE LOGITS
    åĨįæİ¥åĨįåİī
    0.09
    åĨįæİ¥åĨį
    0.09
    åĿļæĮģ
    0.09
    åĬłçłģ
    0.08
    çļĦ解éĩĬ
    0.08
     insiste
    0.08
    å¾ĹæĦı
    0.08
    继ç»Ń
    0.08
    åłħæĮģ
    0.07
     continuar
    0.07
    Activations Density 0.132%

    No Known Activations