© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2621
    Prev
    Next
    INDEX
    Explanations

    percentages and rates per unit

    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
    æ¸ħæ¸ħ
    -0.08
    aney
    -0.08
     Ñĥв
    -0.08
     непод
    -0.08
    ettori
    -0.08
    æĿ¥èĩªä¸ŃåĽ½
    -0.08
    è¦ģä¹Ī
    -0.08
    каде
    -0.08
    åĪ©çī©
    -0.08
    istani
    -0.08
    POSITIVE LOGITS
    ification
    0.06
    pper
    0.06
    åŃľ
    0.06
    .wrap
    0.06
    åĮĸæĪIJ
    0.06
    åĪĨ为
    0.06
    è¡Įäºĭ
    0.05
    æł¹æį®ä¸įåIJĮ
    0.05
    ifying
    0.05
    æķ£
    0.05
    Activations Density 0.004%

    No Known Activations