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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3946
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    qli
    -0.09
    纹
    -0.09
     Mist
    -0.09
    ç¨İåĬ¡
    -0.08
     SOS
    -0.08
    çĽĪ
    -0.08
    Vi
    -0.08
    壮大
    -0.08
    KT
    -0.08
     inspired
    -0.08
    POSITIVE LOGITS
    geries
    0.09
    lot
    0.09
    edium
    0.08
    .zh
    0.08
    bases
    0.08
    inka
    0.08
    inals
    0.08
    ä¸Ģ项
    0.08
    æĢİ
    0.08
    åħ±å»º
    0.08
    Activations Density 0.000%

    No Known Activations