© 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. 2326
    Prev
    Next
    INDEX
    Explanations

    frame, section, products, links, trash, shortest

    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
     sót
    -0.06
    à¹Ħหม
    -0.06
    à¸Ļาย
    -0.06
    æĺŁçº§
    -0.06
    ünt
    -0.06
    nist
    -0.06
    esson
    -0.06
     natomiast
    -0.06
    lés
    -0.06
    uches
    -0.06
    POSITIVE LOGITS
    åį³çĶ¨
    0.09
    æį¢åı¥è¯Ŀ说
    0.08
    æĦıåij³çĿĢ
    0.08
    ãģ¤ãģ¾ãĤĬ
    0.08
    /by
    0.08
    å½¢å¼ıçļĦ
    0.08
     aka
    0.07
    åįļæĸĩ
    0.07
    åį³åĪ°
    0.07
    å½¢å¼ı
    0.07
    Activations Density 0.088%

    No Known Activations