© 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. 59351
    Prev
    Next
    INDEX
    Explanations

    sequential steps in a process

    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
    INDER
    -0.09
    鲫
    -0.09
    ages
    -0.09
    åįĵ
    -0.09
    AGES
    -0.08
    ç¾İ人
    -0.08
    è¾ĥ好
    -0.08
     lut
    -0.08
    çĶ¨éĩı
    -0.08
    quential
    -0.08
    POSITIVE LOGITS
    çĦ¶åIJİ
    0.10
    åIJİåĨį
    0.10
     THEN
    0.09
     undergo
    0.09
    åĨįåĪ°
    0.09
    çĦ¶å¾Į
    0.09
    çŃīä¸Ģç³»åĪĹ
    0.09
    çĦ¶åIJİåĨį
    0.09
    å°±æĪIJäºĨ
    0.09
    èģĮå·¥
    0.09
    Activations Density 0.236%

    No Known Activations