© 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. 41221
    Prev
    Next
    INDEX
    Explanations

    ip-ea

    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
    åĽŀäºĭ
    -0.10
    Ø©
    -0.10
    imiento
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    .microsoft
    -0.09
    nbsp
    -0.08
    à§Ģয়
    -0.08
    ãģĬãĤĬãģ¾ãģĻ
    -0.08
    ../../../
    -0.08
    ê»ĺ
    -0.08
    POSITIVE LOGITS
    RARY
    0.10
    etty
    0.10
    raries
    0.10
    zelf
    0.09
    ergestellt
    0.09
    /her
    0.09
    etahui
    0.09
    tures
    0.09
    waukee
    0.08
    ellaneous
    0.08
    Activations Density 2.967%

    No Known Activations