© 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. 6286
    Prev
    Next
    INDEX
    Explanations

    vessels, law, current, marks, height, wound, amputation

    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
    éĢıè§Ĩ
    -0.10
    çī¹éĤĢ
    -0.09
    éĢı
    -0.09
    æįįåį«
    -0.09
    çī§åľº
    -0.09
    atorial
    -0.09
    à¸Ľà¸£à¸°à¸Ĭา
    -0.09
    èĢģèĻİ
    -0.09
    .mi
    -0.09
    éĻª
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĪĢ
    0.12
    inherits
    0.10
    æĪª
    0.09
    åĪĩæĸŃ
    0.09
    æ¯Ķè¾ĥç®Ģåįķ
    0.09
    okin
    0.09
     level
    0.09
    çķĻ
    0.08
    æ±ģ
    0.08
     ban
    0.08
    Activations Density 0.092%

    No Known Activations