© 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. 63024
    Prev
    Next
    INDEX
    Explanations

    uniform norm, uniformly, queue

    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
    ubbo
    -0.09
    MBER
    -0.09
    puted
    -0.08
    acson
    -0.08
    ivant
    -0.08
    é£İéĽª
    -0.08
    almente
    -0.08
    .Design
    -0.08
    bote
    -0.08
    äºĮè·¯
    -0.08
    POSITIVE LOGITS
    丢
    0.06
     uniformly
    0.06
    大ä¼ļ
    0.06
    æĶ¾å¼ĥäºĨ
    0.06
    manuel
    0.06
    ekar
    0.06
    ur
    0.06
     fin
    0.05
    fr
    0.05
     fr
    0.05
    Activations Density 0.001%

    No Known Activations