© 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. 37516
    Prev
    Next
    INDEX
    Explanations

    percentage

    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
    resta
    -0.09
    ÙĪÙħÙĩ
    -0.08
    ارÙĩ
    -0.08
    ])**
    -0.07
    imuth
    -0.07
    ÅĻe
    -0.07
    IFY
    -0.07
    iors
    -0.07
    à¸Ħู
    -0.07
    _ml
    -0.07
    POSITIVE LOGITS
    %
    0.10
     percent
    0.09
     percentage
    0.08
    %-
    0.08
    percent
    0.08
    %/
    0.08
    ï¼ħ
    0.08
    percentage
    0.08
    -%
    0.07
    .%
    0.07
    Activations Density 0.144%

    No Known Activations