© 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. 18146
    Prev
    Next
    INDEX
    Explanations

    chemical reactions and 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
    boli
    -0.07
    çĥģ
    -0.07
    oader
    -0.07
     gou
    -0.06
    anca
    -0.06
    atty
    -0.06
    _TM
    -0.06
    LoggedIn
    -0.06
     ÑģвоÑĶ
    -0.06
    oa
    -0.06
    POSITIVE LOGITS
    åIJĿ
    0.08
    趣
    0.08
    ustin
    0.07
    æĥľ
    0.07
    bard
    0.07
    å³»
    0.07
    istos
    0.07
    chner
    0.07
    NIK
    0.07
    fris
    0.07
    Activations Density 0.001%

    No Known Activations