© 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. 65282
    Prev
    Next
    INDEX
    Explanations

    Delta

    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
    er
    -0.10
    eru
    -0.09
    ằn
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    als
    -0.09
    erlo
    -0.08
    izontal
    -0.08
    ãĤ±ãĥĥãĥĪ
    -0.08
    à§įতà§ģ
    -0.08
    иÑĤо
    -0.08
    POSITIVE LOGITS
    zelfde
    0.09
    jenigen
    0.09
    ogue
    0.08
    minster
    0.08
    ê¹ĮìļĶ
    0.08
    e
    0.08
    ت
    0.08
    ÚĨÙĩ
    0.07
    ÙĬاط
    0.07
     Masih
    0.07
    Activations Density 0.007%

    No Known Activations