© 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. 24204
    Prev
    Next
    INDEX
    Explanations

    congruent, congratulatory, congenital, congestive

    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
    wards
    -0.10
    ugin
    -0.08
    ÑİÑĢе
    -0.07
    tery
    -0.07
    ters
    -0.07
    amanya
    -0.07
    åģļçļĦå°±æĺ¯
    -0.07
    该类
    -0.07
    ovich
    -0.07
    ByVersion
    -0.07
    POSITIVE LOGITS
    ezza
    0.10
    Ø©
    0.09
    ément
    0.09
    eus
    0.09
    ness
    0.08
    ÙĬØ©
    0.08
    ebet
    0.08
    GLE
    0.08
    ept
    0.08
    ation
    0.08
    Activations Density 0.002%

    No Known Activations