© 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. 764
    Prev
    Next
    INDEX
    Explanations

    process states and outcomes

    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
    丢äºĨ
    -0.11
    éĹŃçݯ
    -0.09
    å±Ĥ次
    -0.09
    æĢµ
    -0.09
    miss
    -0.08
    tics
    -0.08
    TN
    -0.08
    æijŀ
    -0.08
     setattr
    -0.08
    å§Ķ
    -0.08
    POSITIVE LOGITS
    è¿Ľåº¦
    0.13
    è¿ĩç¨ĭ
    0.13
    å®ĮæĪIJåIJİ
    0.12
    è¿ĩç¨ĭä¸Ń
    0.11
    åįĬ天
    0.11
     process
    0.11
    éģİç¨ĭä¸Ń
    0.10
     progress
    0.10
    é¾
    0.10
    çļĦè¿ĩç¨ĭ
    0.10
    Activations Density 0.175%

    No Known Activations