© 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. 16679
    Prev
    Next
    INDEX
    Explanations

    aldehyde and its derivatives

    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
    sek
    -0.08
    TI
    -0.07
    ellini
    -0.07
    ÙħÙĪد
    -0.07
    ÙĬ
    -0.07
    ierra
    -0.07
    çĵ·
    -0.07
    iÅĤ
    -0.07
    å¤ļæĥħ
    -0.07
    i
    -0.07
    POSITIVE LOGITS
    brook
    0.08
    azard
    0.08
    evice
    0.07
    rror
    0.07
    ÑĦек
    0.07
    .px
    0.07
    IRECT
    0.07
    ekh
    0.07
    èij¡èIJĦç³ĸ
    0.07
    زاÙħ
    0.07
    Activations Density 0.012%

    No Known Activations