© 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. 40246
    Prev
    Next
    INDEX
    Explanations

    isotope dilution, chemical shift, spectral response

    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
     intermitt
    -0.08
    пон
    -0.08
    HAS
    -0.08
     Romagna
    -0.08
    Ø·ÙĨ
    -0.08
    .ham
    -0.08
    åIJijèį£
    -0.08
     anonim
    -0.07
     Safety
    -0.07
     Bowl
    -0.07
    POSITIVE LOGITS
    å±ı
    0.07
    两件
    0.07
    çĭĻ
    0.07
    æĶĢ
    0.07
    两级
    0.06
    zel
    0.06
    è¡¡
    0.06
    ikov
    0.06
    åĴĮ第äºĮ
    0.06
     alloy
    0.06
    Activations Density 0.001%

    No Known Activations