© 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. 44272
    Prev
    Next
    INDEX
    Explanations

    so we

    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
    Ïģν
    -0.10
    è¦ģä¹Īæĺ¯
    -0.09
    ppv
    -0.09
    elson
    -0.09
    ulich
    -0.08
    andin
    -0.08
    ffin
    -0.08
    è¦ģä¹Ī
    -0.08
    ISED
    -0.08
    assy
    -0.08
    POSITIVE LOGITS
    符
    0.07
    terior
    0.07
    c
    0.06
    åĻ
    0.06
    Âł
    0.06
    æŃ»
    0.06
    cante
    0.06
     Blok
    0.06
    åįij
    0.05
    Ale
    0.05
    Activations Density 0.043%

    No Known Activations