© 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. 16807
    Prev
    Next
    INDEX
    Explanations

    articles followed by specific nouns

    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
    _GENERIC
    -0.10
     yourselves
    -0.09
    对ç«ĭ
    -0.09
    ç¦ģåĮº
    -0.09
    çľĭçĤ¹
    -0.08
    acceptable
    -0.08
    å±¥
    -0.08
    æĿ¥çľĭçľĭåIJ§
    -0.08
    æ¯ĶæĪij
    -0.08
    天èĬ±
    -0.08
    POSITIVE LOGITS
    åı¸
    0.10
    åı¸é©¬
    0.09
    æ¿ĢçĥĪ
    0.09
    èĭĽ
    0.09
    oker
    0.08
    recent
    0.08
    款
    0.08
    olle
    0.08
    å¾Ĺèµ·
    0.08
    åħ¶æīĢ
    0.08
    Activations Density 0.194%

    No Known Activations