© 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. 31245
    Prev
    Next
    INDEX
    Explanations

    hemodialysis

    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
    çĵľ
    -0.08
    alist
    -0.08
    oglio
    -0.07
    oreal
    -0.07
     dissert
    -0.07
    _MP
    -0.07
    第ä¸Ģéĺ¶æ®µ
    -0.07
     alist
    -0.07
    åĪ¨
    -0.06
    æŀĿ头
    -0.06
    POSITIVE LOGITS
     weekly
    0.24
    æ¯ı次
    0.23
     regularly
    0.23
    å®ļæľŁ
    0.23
    æ¯ıåij¨
    0.23
     periodically
    0.22
    å®ļæľŁçļĦ
    0.22
    æ¯ıæľĪ
    0.22
     periodic
    0.21
     monthly
    0.21
    Activations Density 0.911%

    No Known Activations