© 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. 63913
    Prev
    Next
    INDEX
    Explanations

    discharging reservoir, airbag cushion, barrier, filters, jet flows, quilt parts, divisions (JS), relationships

    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
    åĪ»
    -0.10
    ç¢İ
    -0.10
    æij§æ¯ģ
    -0.09
    utherland
    -0.09
    loggedin
    -0.09
    ç¢İçīĩ
    -0.09
    çļĦçľ¼åħī
    -0.09
    æĶ¾å¤§
    -0.09
     Born
    -0.09
    adera
    -0.08
    POSITIVE LOGITS
    çİĭåŃIJ
    0.09
    å¼łæī¬
    0.09
    odom
    0.09
    绸
    0.09
    æĸĽ
    0.08
    æ¼Ĥ
    0.08
    åŃĺåľ¨éĹ®é¢ĺ
    0.08
    çĮľæĥ³
    0.08
    åıijçİ°éĹ®é¢ĺ
    0.08
    ç¼ĵåĨ²
    0.08
    Activations Density 0.098%

    No Known Activations