© 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. 41617
    Prev
    Next
    INDEX
    Explanations

    polar coordinates

    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
    .now
    -0.07
    trin
    -0.07
    lain
    -0.07
    æĸ¹
    -0.06
    åŃķ
    -0.06
    ile
    -0.06
    krim
    -0.06
    ]("
    -0.06
    å¤į
    -0.06
    ä¸Ģ次次
    -0.06
    POSITIVE LOGITS
    æł¡åĽŃçݯå¢ĥ
    0.08
    erde
    0.07
    erden
    0.07
    çµĤ
    0.07
    ostra
    0.07
    getDb
    0.07
    æŁ¥éĩį
    0.07
    argin
    0.07
    ej
    0.07
    éĩijæĸ¯
    0.07
    Activations Density 0.002%

    No Known Activations