© 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. 8615
    Prev
    Next
    INDEX
    Explanations

    heterocyclic rings containing `ox`, `az`, `ir`

    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
    ÙĪرÙĬ
    -0.07
    亮
    -0.07
    ãĥŀãĤ¬
    -0.07
     dominante
    -0.07
    æĹ©
    -0.07
    ulu
    -0.07
    åĺ¶
    -0.07
    yj
    -0.07
    ëł¹
    -0.07
    ç¾¹
    -0.07
    POSITIVE LOGITS
    ç¼ļ
    0.08
    å©¿
    0.06
     family
    0.06
     genannte
    0.06
    éĨļ
    0.06
     autom
    0.06
     Walsh
    0.06
     diagram
    0.06
    ...”
    0.06
    ierz
    0.06
    Activations Density 0.016%

    No Known Activations