© 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. 752
    Prev
    Next
    INDEX
    Explanations

    names followed by colon or url

    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
    “
    -0.07
    -Disposition
    -0.07
    ti
    -0.07
    Y
    -0.07
    -
    -0.07
    arn
    -0.06
    &
    -0.06
    ä½ı
    -0.06
    åĴ¬
    -0.06
    ä¿ĥ
    -0.06
    POSITIVE LOGITS
    @gmail
    0.09
     **—
    0.08
    aturen
    0.08
    resents
    0.08
    estig
    0.08
    yku
    0.08
     undermin
    0.08
    everd
    0.08
    resco
    0.08
    vents
    0.08
    Activations Density 0.279%

    No Known Activations