© 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. 18098
    Prev
    Next
    INDEX
    Explanations

    nutrient cycling

    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
    åĺİ
    -0.07
    äss
    -0.07
    æĹĹ
    -0.07
    ETT
    -0.07
    iac
    -0.07
    è±IJ
    -0.07
    åħ¶ä¹IJ
    -0.07
    輩
    -0.07
    .Flag
    -0.07
    ĻĤ
    -0.07
    POSITIVE LOGITS
    ä¹ĭå¤ĸ
    0.07
    æ°´ä»Ļ
    0.07
    bid
    0.07
    仲
    0.07
    åĪ©çļĦ
    0.07
    —but
    0.07
    å°±ç®ĹäºĨ
    0.07
    —and
    0.07
    —including
    0.07
    以å¤ĸ
    0.07
    Activations Density 0.797%

    No Known Activations