© 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. 32444
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ¸ħæ¥ļçļĦ
    -0.07
     rè
    -0.07
    onge
    -0.06
     dur
    -0.06
    ons
    -0.06
    .sb
    -0.06
    beth
    -0.06
    uzzi
    -0.06
    _OW
    -0.06
    é«ĺæŃĮ
    -0.06
    POSITIVE LOGITS
    èĵ®
    0.08
    à¹Į
    0.07
    èĩªå·±èĥ½
    0.07
     keham
    0.07
    itet
    0.07
     sánh
    0.07
    _nn
    0.07
     '::
    0.07
    irn
    0.07
    æĪijä¸Ģ个人
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.