© 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. 9673
    Prev
    Next
    INDEX
    Explanations

    chemical group prefixes and abbreviations

    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
    á»ĥn
    -0.07
    ForObject
    -0.07
    家åºĦ
    -0.06
    KF
    -0.06
    ç²Ĺç²®
    -0.06
    'L
    -0.06
    en
    -0.06
    biot
    -0.06
    éĵIJ
    -0.06
    8
    -0.06
    POSITIVE LOGITS
    veld
    0.08
    ugh
    0.08
    ìĪł
    0.08
    ovre
    0.08
    azar
    0.08
    ظÙĩ
    0.07
    маÑħ
    0.07
    saan
    0.07
    ITION
    0.07
    ieder
    0.07
    Activations Density 0.005%

    No Known Activations