© 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. 39625
    Prev
    Next
    INDEX
    Explanations

    stating or stating changes

    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
    vista
    -0.09
    ණ
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    CIAL
    -0.08
    หà¸Ļà¹īาà¸Ļีà¹ī
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    thest
    -0.07
    rama
    -0.07
    kwargs
    -0.07
    POSITIVE LOGITS
    ewart
    0.10
    edly
    0.09
     ulang
    0.08
    istical
    0.08
    epend
    0.08
    عاÙĦ
    0.08
    çĻ½äºĨ
    0.08
    à¸ģารà¸ĵà¹Į
    0.08
    alker
    0.07
     bahwa
    0.07
    Activations Density 0.012%

    No Known Activations