© 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. 60595
    Prev
    Next
    INDEX
    Explanations

    father or mother of

    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
    aland
    -0.10
    İĺìĿ´
    -0.10
    unchecked
    -0.10
    lauf
    -0.09
    .getCount
    -0.09
    .Standard
    -0.09
    anko
    -0.09
    åĨ¶
    -0.09
    ookie
    -0.09
    oons
    -0.09
    POSITIVE LOGITS
    溯
    0.10
    çĪ·
    0.08
     Henderson
    0.08
    çĦ¶æĺ¯
    0.08
    èĪ¬
    0.08
    å¥łå®ļ
    0.08
    hei
    0.08
     bast
    0.08
    åĩ¤åĩ°
    0.08
    款
    0.08
    Activations Density 0.021%

    No Known Activations