© 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. 47423
    Prev
    Next
    INDEX
    Explanations

    power

    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
    uset
    -0.09
    æĻĶ
    -0.08
    æĹłçŁ¥
    -0.08
     dated
    -0.08
    elia
    -0.08
    ราว
    -0.08
    æĮij
    -0.08
    ush
    -0.08
    лаг
    -0.08
    ubo
    -0.08
    POSITIVE LOGITS
    iger
    0.11
    orsch
    0.10
    士
    0.10
     BDS
    0.10
    iously
    0.09
    letes
    0.09
    横
    0.09
    åĬ¿
    0.09
    æ¾¹
    0.09
    缸åĬ©
    0.09
    Activations Density 0.002%

    No Known Activations