© 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. 62098
    Prev
    Next
    INDEX
    Explanations

    mass spectrometry

    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
    æľĪåŃIJ
    -0.07
    åįĹåĽ½
    -0.07
    羣å¿ĥçļĦ
    -0.07
    æ¥ŀ
    -0.06
     TTC
    -0.06
     ~=
    -0.06
    rical
    -0.06
    ksz
    -0.06
    éĩij鸡
    -0.06
    kina
    -0.06
    POSITIVE LOGITS
    质谱
    0.11
    è½°
    0.09
     peptide
    0.08
    /ion
    0.08
    à¹Ģà¸Ħรืà¹Īà¸Ńà¸ĩ
    0.08
     fragmentation
    0.08
    注åĨĮåı·
    0.08
    ToObject
    0.08
     ì°į
    0.08
     Fragment
    0.07
    Activations Density 0.074%

    No Known Activations