© 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. 60573
    Prev
    Next
    INDEX
    Explanations

    hydro- followed by certain endings or words

    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
    åŃIJéĩĮ
    -0.11
    ned
    -0.11
    èĽ¾
    -0.09
    æĿ¼
    -0.09
    owing
    -0.09
    æ¹ĸåĮº
    -0.09
     Câm
    -0.09
    exe
    -0.09
    ç¹ĩ
    -0.09
    ctors
    -0.09
    POSITIVE LOGITS
    ly
    0.12
    çĦ¶æĺ¯
    0.11
    plet
    0.10
    line
    0.10
    omic
    0.09
    è¡·
    0.09
    ãģĹãģ¾ãģĨ
    0.09
    hack
    0.09
    neath
    0.08
    zeit
    0.08
    Activations Density 0.062%

    No Known Activations