© 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. 59252
    Prev
    Next
    INDEX
    Explanations

    problem-solving skills

    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
    ILLE
    -0.10
    erator
    -0.10
    æĬĵ好
    -0.09
    åľĪ
    -0.09
    .mov
    -0.09
    .dump
    -0.09
    ted
    -0.09
    é¹°
    -0.08
    inish
    -0.08
    åĽ½æĥħ
    -0.08
    POSITIVE LOGITS
    æ£ĺ
    0.12
    解åĨ³éĹ®é¢ĺ
    0.12
    解åĨ³æĸ¹æ¡Ī
    0.12
    çªģåĩºéĹ®é¢ĺ
    0.11
     solutions
    0.11
    解決
    0.11
    解åĨ³
    0.10
    å¤įæĿĤçļĦ
    0.10
     solving
    0.10
    åĩºè·¯
    0.09
    Activations Density 0.019%

    No Known Activations