© 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. 12110
    Prev
    Next
    INDEX
    Explanations

    breakdown of components

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĬĦ
    -0.09
    è¶ķ
    -0.09
    Ñģли
    -0.08
    ä¸Ī
    -0.08
    线索
    -0.08
    红线
    -0.08
    çĦ¶åIJİåĨį
    -0.08
    ä¸Ģç«Ļå¼ı
    -0.08
    cert
    -0.08
    æݼ
    -0.08
    POSITIVE LOGITS
    åĪĨå¸ĥ
    0.17
     breakdown
    0.15
    æĺİç»Ĩ
    0.13
    æŀĦæĪIJ
    0.12
     distribution
    0.12
    å¦Ĥä¸ĭ
    0.10
     Distribution
    0.10
    æĥħåĨµ
    0.10
    ç»ĨåĪĨ
    0.10
    distribution
    0.10
    Activations Density 0.107%

    No Known Activations