© 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. 50659
    Prev
    Next
    INDEX
    Explanations

    compounds ending in ide or chloride

    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
    ness
    -0.13
    о
    -0.10
    shots
    -0.09
    ned
    -0.09
    à¹Ĩ
    -0.09
    ÏĤ
    -0.09
    Ø©
    -0.09
    o
    -0.09
    nable
    -0.09
    spot
    -0.09
    POSITIVE LOGITS
    zelfde
    0.10
    irected
    0.08
    IRECT
    0.08
    Ľ
    0.08
    à¦ĩ
    0.07
    owler
    0.07
    asure
    0.07
    ibas
    0.07
    velopment
    0.07
    оÑģÑĤи
    0.07
    Activations Density 0.037%

    No Known Activations