© 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. 60559
    Prev
    Next
    INDEX
    Explanations

    know how or what

    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
    æĭľ
    -0.09
    ilight
    -0.09
     wonder
    -0.09
    æ®Ľ
    -0.09
    izo
    -0.09
    onden
    -0.08
     Brace
    -0.08
    å¤§éĽ¨
    -0.08
    é«ĺ强度
    -0.08
    åĨįçĶŁ
    -0.08
    POSITIVE LOGITS
    æĩĤ
    0.17
    æĩĤå¾Ĺ
    0.16
    çŁ¥éģĵèĩªå·±
    0.16
    çŁ¥éģĵ
    0.15
     knows
    0.13
    ä¸įæĩĤ
    0.13
    è°Ļ
    0.13
    know
    0.13
     знаеÑĤ
    0.13
     Know
    0.12
    Activations Density 0.072%

    No Known Activations