© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60580
    Prev
    Next
    INDEX
    Explanations

    defense and defence words

    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
    Negative Logits
    åĦ¿
    -0.12
    keit
    -0.11
    ../../../
    -0.11
    主æĦı
    -0.10
    åħĴ
    -0.09
    ting
    -0.09
    orris
    -0.09
    erator
    -0.09
    ollo
    -0.09
    TING
    -0.09
    POSITIVE LOGITS
    less
    0.13
    ably
    0.10
    ì±ħ
    0.10
    bite
    0.09
    ÙĬات
    0.09
    full
    0.09
    pirit
    0.09
    -conscious
    0.09
    ×Ļ×ķת
    0.09
    conde
    0.09
    Activations Density 0.021%

    No Known Activations