© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41635
    Prev
    Next
    INDEX
    Explanations

    give the variable

    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
    Not in Any Lists

    No Comments

    Negative Logits
     avs
    -0.08
    aign
    -0.07
    affles
    -0.07
    onsel
    -0.07
    è¯ķçĶ¨
    -0.07
    AVED
    -0.07
    -align
    -0.07
    ragon
    -0.07
     Kek
    -0.07
    empor
    -0.07
    POSITIVE LOGITS
     counted
    0.09
     counting
    0.09
    计æķ°
    0.09
    測
    0.08
    rome
    0.08
    Count
    0.08
     count
    0.08
    .count
    0.07
     Count
    0.07
    count
    0.07
    Activations Density 0.037%

    No Known Activations