© 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. 18799
    Prev
    Next
    INDEX
    Explanations

    commercials and daily practices

    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
    寮
    -0.09
    awang
    -0.08
    åĮĸçī©
    -0.08
    igno
    -0.08
    resso
    -0.08
    iosk
    -0.07
    åĿļå®ļçIJĨæĥ³ä¿¡å¿µ
    -0.07
    áºłN
    -0.07
    ẻ
    -0.07
    æĹ¥åħ¬å¸ĥ
    -0.07
    POSITIVE LOGITS
    _sem
    0.08
    agens
    0.07
    omatic
    0.07
    éĵ
    0.06
    zer
    0.06
    ku
    0.06
    æĿ¥è¯´
    0.06
    ist
    0.06
    ium
    0.06
    è¢ħ
    0.06
    Activations Density 0.023%

    No Known Activations