© 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. 18447
    Prev
    Next
    INDEX
    Explanations

    redox reactions

    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
    nisse
    -0.07
    .ny
    -0.07
    림
    -0.07
    æ²ģ
    -0.07
    hä
    -0.07
    å¾·åĭĴ
    -0.07
    ók
    -0.07
     ÑĥдобÑģÑĤва
    -0.07
    éĢīæ´¾
    -0.07
    娥
    -0.06
    POSITIVE LOGITS
     oxidation
    0.10
     oxid
    0.10
    æ°§åĮĸ
    0.09
    æĺĩ
    0.08
    oxid
    0.08
     catal
    0.08
    лек
    0.08
    è¿ĺåİŁ
    0.08
    ¶
    0.07
     Ox
    0.07
    Activations Density 0.012%

    No Known Activations