© 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. 55929
    Prev
    Next
    INDEX
    Explanations

    elastic properties, fibers, recovery, resistance, Search

    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
    ÙĦع
    -0.09
    zzle
    -0.07
    èļ£
    -0.07
    ftar
    -0.07
    à¸Ķย
    -0.07
    edException
    -0.07
    ester
    -0.06
    ãģĸãģ¾
    -0.06
    онов
    -0.06
     else
    -0.06
    POSITIVE LOGITS
    ibility
    0.10
    raries
    0.09
    atable
    0.08
    quent
    0.08
    encontre
    0.08
    ities
    0.08
    iola
    0.08
    izabeth
    0.08
    worth
    0.08
    ://%
    0.08
    Activations Density 0.020%

    No Known Activations