© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14066
    Prev
    Next
    INDEX
    Explanations

    excit or excitatory

    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
    zinho
    -0.09
    igans
    -0.09
    ôm
    -0.08
    owing
    -0.08
    mite
    -0.08
    ÙĨÙĬÙĨ
    -0.08
    ality
    -0.08
    esco
    -0.08
    tery
    -0.08
    å¯Įç¿ģ
    -0.08
    POSITIVE LOGITS
    uation
    0.10
    uat
    0.09
    aneous
    0.09
    uated
    0.09
    uous
    0.08
    uates
    0.08
    uations
    0.08
    uating
    0.08
    åIJijèį£
    0.08
    ercise
    0.08
    Activations Density 0.050%

    No Known Activations