© 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. 56107
    Prev
    Next
    INDEX
    Explanations

    function or code timing

    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
    ISED
    -0.08
    riz
    -0.07
    å¤ļåģļ
    -0.07
    ori
    -0.07
    auc
    -0.07
    rzy
    -0.07
    tti
    -0.07
     dius
    -0.07
    cesi
    -0.07
    åŁºéĩij管çIJĨ
    -0.07
    POSITIVE LOGITS
    iglie
    0.07
    Tpl
    0.06
    Ľ°
    0.06
    å±
    0.06
    OutOfRange
    0.06
    èĩ¼
    0.06
    ົ
    0.06
    igel
    0.06
    ห
    0.06
    <small
    0.06
    Activations Density 0.061%

    No Known Activations