© 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. 38062
    Prev
    Next
    INDEX
    Explanations

    aromatic chemistry

    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
    Åijl
    -0.10
    à¸Ĺà¹Į
    -0.09
    Ùĭ
    -0.09
    Ù°
    -0.09
    aneous
    -0.09
    icismo
    -0.08
    itaire
    -0.08
    hares
    -0.08
    warzys
    -0.08
    ../
    -0.08
    POSITIVE LOGITS
    ity
    0.12
    keit
    0.08
    ness
    0.08
    ITY
    0.07
    ogenic
    0.07
    ella
    0.07
    åŃ£
    0.07
    à§įম
    0.07
    icity
    0.07
    us
    0.07
    Activations Density 0.004%

    No Known Activations