© 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. 59799
    Prev
    Next
    INDEX
    Explanations

    estimation of effects

    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
    å¾ģ
    -0.07
     hina
    -0.07
     goc
    -0.07
    alda
    -0.07
    Mahon
    -0.07
    inspace
    -0.07
    uzz
    -0.07
    abin
    -0.07
     Erect
    -0.07
     اÙĦتخ
    -0.07
    POSITIVE LOGITS
    ÑĦиÑĢ
    0.08
    ä¸ĭ课
    0.08
    heen
    0.07
    UNCH
    0.07
    ron
    0.07
    º
    0.07
     Davidson
    0.07
    秽
    0.07
    æļ´
    0.07
    yak
    0.07
    Activations Density 0.010%

    No Known Activations