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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8126
    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
    els
    -0.09
    åħ¶æīĢ
    -0.08
     done
    -0.08
    JR
    -0.08
     tal
    -0.08
    lab
    -0.08
    禾
    -0.08
    æijĦ
    -0.08
    tal
    -0.08
    宣
    -0.08
    POSITIVE LOGITS
    èĪIJ
    0.11
    éĢ¡
    0.11
     оÑĩеÑĢ
    0.11
    egis
    0.10
    è·»
    0.10
     Gingrich
    0.10
    _beh
    0.10
    .rpm
    0.09
    éĺŁåijĺ们
    0.09
    æĸ°ç¯ĩç«ł
    0.09
    Activations Density 0.000%

    No Known Activations