© 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. 26445
    Prev
    Next
    INDEX
    Explanations

    volatile organic compounds

    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
    æĦıçļĦ
    -0.07
    esis
    -0.07
    åįļçī©éĻ¢
    -0.07
    OrUpdate
    -0.07
    OrElse
    -0.07
     Ñģобой
    -0.06
    avanaugh
    -0.06
    åĬŀçļĦ
    -0.06
    nop
    -0.06
    Converted
    -0.06
    POSITIVE LOGITS
    olatile
    0.10
    kony
    0.09
    edback
    0.09
    æĢ§çļĦ
    0.09
    èĴ¸èĴ¸
    0.09
    à¸Ĭืà¹Īà¸Ļ
    0.08
    enburg
    0.08
    ocity
    0.08
    anguages
    0.08
    íľĺ
    0.08
    Activations Density 0.015%

    No Known Activations