© 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. 43043
    Prev
    Next
    INDEX
    Explanations

    metal, oxide, or complex names

    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
    æĢ§æĪĸ
    -0.09
    æĢ§ä»¥åıĬ
    -0.08
    reden
    -0.08
    æĢ§éĹ®é¢ĺ
    -0.08
    æĢ§å·¥ä½ľ
    -0.08
    æĢ§åıĬ
    -0.08
    olit
    -0.07
    æĢ§çŃī
    -0.07
    æĢ§åĬŁèĥ½
    -0.07
    TRACT
    -0.07
    POSITIVE LOGITS
     dioxide
    0.09
    ä¸Ģ声
    0.07
    è´°
    0.07
    åıĪ称
    0.07
    oxide
    0.06
    _COMPLEX
    0.06
    çļĦæĦıæĢĿ
    0.06
    ľ
    0.06
    _HEADERS
    0.06
    ·
    0.06
    Activations Density 0.035%

    No Known Activations