© 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. 26389
    Prev
    Next
    INDEX
    Explanations

    sagebrush, mage's, Vale Railway

    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
    edian
    -0.10
    åİ®
    -0.10
    ss
    -0.10
    åīįçŀ»
    -0.09
    sov
    -0.09
    æĢ
    -0.09
    sss
    -0.08
    æĭ¥æĬ¤
    -0.08
     sheer
    -0.08
    lying
    -0.08
    POSITIVE LOGITS
    brush
    0.16
    0.16
    人士
    0.11
    acre
    0.10
    ication
    0.09
    keepers
    0.09
     Ñĥзн
    0.09
    istry
    0.09
    iores
    0.09
    اء
    0.09
    Activations Density 0.005%

    No Known Activations