© 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. 50083
    Prev
    Next
    INDEX
    Explanations

    binding, porphyrin, and chelating ligands

    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
    گاÙĩ
    -0.07
    icin
    -0.07
    arent
    -0.07
    æŃ£çļĦ
    -0.06
     Blast
    -0.06
     اÙĦرÙħ
    -0.06
    alize
    -0.06
    èĪįå¾Ĺ
    -0.06
     rest
    -0.06
     mot
    -0.06
    POSITIVE LOGITS
    BIND
    0.08
    ä¿Ŀ驾
    0.08
    ainter
    0.08
    簡稱
    0.08
    çįĦ
    0.07
    çĭ±
    0.07
    -binding
    0.07
     binding
    0.07
    åħĭåĬĽ
    0.07
    ÑĤеÑĤ
    0.07
    Activations Density 0.071%

    No Known Activations