© 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. 26248
    Prev
    Next
    INDEX
    Explanations

    good at 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
    æľĢéĩįè¦ģ
    -0.09
    å¤ĸåĮħ
    -0.09
    íĭĢ
    -0.08
    atta
    -0.08
    bulk
    -0.08
    .bulk
    -0.08
    æľĢéĩįè¦ģçļĦ
    -0.08
    æļ´
    -0.08
    æ³°
    -0.08
    /repos
    -0.08
    POSITIVE LOGITS
    æĵħéķ¿
    0.20
    æĵħ
    0.13
     giá»ıi
    0.13
    çī¹éķ¿
    0.12
     adept
    0.12
    åģļå¾Ĺ
    0.12
    æľ¬é¢Ĩ
    0.11
    ç²¾éĢļ
    0.11
    skills
    0.11
    åĸĦäºİ
    0.11
    Activations Density 0.074%

    No Known Activations