© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44353
    Prev
    Next
    INDEX
    Explanations

    R. Clark

    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
    Negative Logits
    ãģĹãĤĤ
    -0.09
    quel
    -0.08
    สà¹Į
    -0.08
    onom
    -0.08
    besch
    -0.08
    ãģĹãĤĩ
    -0.08
     prescind
    -0.08
    ÑģÑĤва
    -0.08
    stash
    -0.08
    _EMIT
    -0.08
    POSITIVE LOGITS
     However
    0.07
     if
    0.06
    ÑĢаÑĩи
    0.06
    rey
    0.06
    H
    0.06
    缸è¾ħ缸æĪIJ
    0.06
    ================================================
    0.06
    gia
    0.06
    'e
    0.06
    	if
    0.06
    Activations Density 0.001%

    No Known Activations