© 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. 6297
    Prev
    Next
    INDEX
    Explanations

    door locks and entries

    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
    å¼ĢéŨ
    -0.11
     gate
    -0.10
    大éŨ
    -0.10
     Gate
    -0.10
     door
    -0.10
     gates
    -0.09
    ipt
    -0.09
    éŨåı£
    -0.09
    å¼Ģåı£
    -0.09
    asan
    -0.09
    POSITIVE LOGITS
    PropertyParams
    0.09
    à¹Ħà¸ĭ
    0.08
     Darling
    0.08
    yms
    0.08
     Trainer
    0.08
    å°±ä¸įä¼ļ
    0.08
    uden
    0.08
    çĭĤ
    0.08
     Ñģли
    0.08
    ernel
    0.08
    Activations Density 0.023%

    No Known Activations