© 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. 14133
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and biological substances

    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
     dominated
    -0.07
     Vidal
    -0.06
    JAKARTA
    -0.06
    ÙħاÙħ
    -0.06
    -going
    -0.06
    çŀ¥
    -0.06
    Ñıн
    -0.06
    åĽłä¸ºæľī
    -0.06
    uche
    -0.06
     Kör
    -0.06
    POSITIVE LOGITS
    çļĦä½ľçĶ¨ä¸ĭ
    0.09
    åIJ«éĩıé«ĺ
    0.08
     responsible
    0.08
     responsables
    0.08
    çĶ¨ä»¥
    0.08
    à¸Ĭืà¹Īà¸Ńวà¹Īา
    0.08
    nown
    0.08
    æķĻèĤ²åѦéĻ¢
    0.07
     коÑĤоÑĢÑĭе
    0.07
     sayesinde
    0.07
    Activations Density 0.146%

    No Known Activations