© 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. 48828
    Prev
    Next
    INDEX
    Explanations

    properly/proper

    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
    -0.10
    urope
    -0.10
    å¿ĺè¿Ķ
    -0.09
    ToProps
    -0.09
    satz
    -0.09
    aspers
    -0.09
    stra
    -0.09
    apo
    -0.09
    à¹Īà¸Ļ
    -0.09
    taler
    -0.09
    POSITIVE LOGITS
    ly
    0.11
    fully
    0.10
    er
    0.09
    ity
    0.09
    o
    0.09
    cy
    0.08
    idge
    0.08
    ately
    0.08
    ment
    0.08
    -looking
    0.08
    Activations Density 0.015%

    No Known Activations