© 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. 59272
    Prev
    Next
    INDEX
    Explanations

    center

    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
    esome
    -0.10
    setter
    -0.10
     Nadu
    -0.09
    nak
    -0.09
    antha
    -0.09
    elan
    -0.09
    athon
    -0.09
    apor
    -0.09
    cess
    -0.09
    cape
    -0.09
    POSITIVE LOGITS
    ally
    0.12
    åĨħçļĦ
    0.11
    çļ¿
    0.09
    prises
    0.09
    ial
    0.09
    人士
    0.09
    åī¯ä¸»ä»»
    0.09
    ä¸Ģè§Ĵ
    0.09
    oids
    0.08
    ogn
    0.08
    Activations Density 0.041%

    No Known Activations