© 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. 576
    Prev
    Next
    INDEX
    Explanations

    delivered items

    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
    onz
    -0.10
    楯
    -0.10
    æĭĽå¾ħ
    -0.09
    涵çĽĸäºĨ
    -0.09
    erton
    -0.09
    à¸Ńà¸Ļ
    -0.09
    èµĬ
    -0.09
    åīįä¸ī
    -0.09
    è±¹
    -0.09
    æŃĩ
    -0.09
    POSITIVE LOGITS
     rele
    0.09
    .std
    0.08
    ç¬Ī
    0.08
    éĢģå¾Ģ
    0.08
    ãĤĤãģ®ãģ®
    0.08
    usto
    0.08
    _stdio
    0.08
    chu
    0.08
     Lesser
    0.08
    ellung
    0.08
    Activations Density 0.001%

    No Known Activations