© 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. 29424
    Prev
    Next
    INDEX
    Explanations

    offense scheme

    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
    æĥľ
    -0.09
    ç²ī
    -0.09
    üss
    -0.09
     trib
    -0.09
    æļĤ
    -0.08
    æķĪ
    -0.08
    ç´łè´¨
    -0.08
     Mic
    -0.08
     declared
    -0.08
    yect
    -0.08
    POSITIVE LOGITS
     Porter
    0.10
    红åĪ©
    0.10
    LayoutManager
    0.10
    å¸ĥç½®
    0.09
    æĪĺæľ¯
    0.09
    è¤Ĵ
    0.09
    rut
    0.09
    ÕŃ
    0.09
    влад
    0.09
    éĵį
    0.09
    Activations Density 0.066%

    No Known Activations