© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56804
    Prev
    Next
    INDEX
    Explanations

    civilizations or civil war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¤í
    -0.11
    ingly
    -0.10
    ivity
    -0.10
    onium
    -0.09
    manship
    -0.09
    sgiving
    -0.09
     зÑĢениÑı
    -0.09
    åĽ¢éķ¿
    -0.09
    äll
    -0.09
    osing
    -0.09
    POSITIVE LOGITS
    izational
    0.12
    itas
    0.11
    rary
    0.10
    trl
    0.10
    宪
    0.09
    aries
    0.09
    èĨĬ
    0.09
    ÙĬا
    0.09
    aires
    0.09
    wyn
    0.09
    Activations Density 0.015%

    No Known Activations