© 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. 29734
    Prev
    Next
    INDEX
    Explanations

    peculiar

    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
    baugh
    -0.09
    roots
    -0.09
    cape
    -0.09
    manship
    -0.08
    çıIJ
    -0.08
    itre
    -0.08
    èĥĸåŃIJ
    -0.08
    æĪĬ
    -0.08
    anel
    -0.08
    scape
    -0.08
    POSITIVE LOGITS
    ities
    0.12
    chio
    0.12
    ties
    0.11
    ç±½
    0.10
    ity
    0.09
    累累
    0.09
    姿åĬ¿
    0.09
     обÑĢазом
    0.09
    ials
    0.09
    ogy
    0.09
    Activations Density 0.004%

    No Known Activations