© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9340
    Prev
    Next
    INDEX
    Explanations

    prenatal diagnosis and pregnancy

    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
    è°ĥåĬ¨
    -0.10
    zc
    -0.09
    转移
    -0.09
    _hop
    -0.09
    _DUMP
    -0.09
    转载
    -0.09
    çłļ
    -0.08
    çļij
    -0.08
    乡
    -0.08
     dual
    -0.08
    POSITIVE LOGITS
    å¼±
    0.09
    isce
    0.09
    é«ĺç´łè´¨
    0.09
    å¯¹æľªæĿ¥
    0.09
    çĨĶ
    0.08
    对åŃ©åŃIJ
    0.08
    æľºèĥ½
    0.08
    天èĬ±
    0.08
    çĺ¸
    0.08
     desc
    0.08
    Activations Density 0.049%

    No Known Activations