© 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. 26052
    Prev
    Next
    INDEX
    Explanations

    drug, agents, plants, fixed, secured

    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
    ighted
    -0.09
    imulator
    -0.09
    ä¸İä¸ŃåĽ½
    -0.09
    çľ¼è§Ĵ
    -0.08
    alice
    -0.08
    åŃĺéĩı
    -0.08
    è®¤çŁ¥
    -0.08
    ÑĢиÑģÑĤ
    -0.08
    .Tick
    -0.08
     precip
    -0.08
    POSITIVE LOGITS
    使ä¹ĭ
    0.11
    使åħ¶
    0.11
    åľ¨éĩĮéĿ¢
    0.11
    æĶ¾è¿Ľ
    0.10
    åīįæĿ¥
    0.10
    ä¸ĬéŨ
    0.10
    诸å¦Ĥ
    0.10
    ä¸Ĭåİ»
    0.09
    亲
    0.09
    asma
    0.09
    Activations Density 0.420%

    No Known Activations