© 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. 31021
    Prev
    Next
    INDEX
    Explanations

    masks and face coverings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æİ£
    -0.11
    注åħ¥
    -0.10
    æµģåĩº
    -0.09
    å®´
    -0.09
    åıĭæĥħ
    -0.09
    汩
    -0.09
    chip
    -0.09
     Gew
    -0.08
    æĶĺ
    -0.08
    æµģåħ¥
    -0.08
    POSITIVE LOGITS
     mask
    0.22
     masks
    0.20
    éĿ¢åħ·
    0.20
    åı£ç½©
    0.20
    mask
    0.20
    _mask
    0.18
     Masks
    0.18
    -mask
    0.17
    .mask
    0.17
    Mask
    0.16
    Activations Density 0.050%

    No Known Activations