© 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. 26076
    Prev
    Next
    INDEX
    Explanations

    distributed decentralized app infrastructure

    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
    idth
    -0.09
     sm
    -0.09
    æģ¯æģ¯
    -0.09
     ÑģовеÑĢ
    -0.09
    ç´§è·Ł
    -0.08
    æĦŁ
    -0.08
    æĺİåªļ
    -0.08
    éķĸ
    -0.08
    olvency
    -0.08
    iPad
    -0.08
    POSITIVE LOGITS
    èĪħèĪħ
    0.10
    ç»ĵæŀĦæĢ§
    0.09
    ivable
    0.08
    åĿ¦
    0.08
    æĸŃè£Ĥ
    0.08
     decentral
    0.08
    æĸŃ
    0.08
    èĻİ
    0.08
    Unchecked
    0.08
    第ä¸ī
    0.08
    Activations Density 0.156%

    No Known Activations