© 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. 4371
    Prev
    Next
    INDEX
    Explanations

    Intel Series, COMECON, movement

    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
    ryptography
    -0.09
    agio
    -0.08
    ä¸Ģå¦Ĥ
    -0.08
    upply
    -0.08
     admit
    -0.08
    chg
    -0.08
    ë¡Ģ
    -0.08
    anyi
    -0.07
    女巫
    -0.07
    abung
    -0.07
    POSITIVE LOGITS
    âĦ¢
    0.10
    ®
    0.09
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.09
     which
    0.08
     whereby
    0.08
    以åıĬåIJĦç§į
    0.08
    lyn
    0.07
    —which
    0.07
    baum
    0.06
     ®
    0.06
    Activations Density 0.193%

    No Known Activations