© 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. 45590
    Prev
    Next
    INDEX
    Explanations

    given by

    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
    Ø®ÙĨ
    -0.08
    zil
    -0.08
    avais
    -0.08
    æĺ¥æĿ¥
    -0.08
    à¸Īัà¸ĩ
    -0.08
    Ø®
    -0.07
    alité
    -0.07
    пиÑģÑĮ
    -0.07
    ests
    -0.07
    мÑı
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæĸ¹å¼ı
    0.10
    åħ¬å¼ı
    0.08
     either
    0.07
    以ä¸ĭãģ®
    0.07
    è¦ģä¹Ī
    0.06
    å¦Ĥä¸ĭ
    0.06
    æŦ
    0.06
    å¿ĥå¾Ĺ
    0.06
     saying
    0.06
    der
    0.06
    Activations Density 0.012%

    No Known Activations