© 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. 9060
    Prev
    Next
    INDEX
    Explanations

    dissoci, dissolved, dissolution

    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
    æĺ¯éĽĨ
    -0.07
    &R
    -0.07
     overrun
    -0.07
    ä¸įè¦ģ被
    -0.07
    cou
    -0.07
    ä¹ĭæ¯į
    -0.07
    odef
    -0.07
     chron
    -0.07
    æĺ¯åħ¨çIJĥ
    -0.07
    éĢ¼è¿ij
    -0.07
    POSITIVE LOGITS
     dissoci
    0.10
    溶äºİæ°´
    0.08
    溶解
    0.08
     dissolution
    0.08
    åĴ¸
    0.08
     dissolved
    0.08
     ions
    0.08
    离åŃIJ
    0.08
    溶äºİ
    0.08
    æĭĨåĪĨ
    0.08
    Activations Density 0.002%

    No Known Activations