© 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. 60554
    Prev
    Next
    INDEX
    Explanations

    auricular, ears, temporal, axillary

    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
    裱
    -0.10
     ÙĪاÙĦع
    -0.10
    UniqueId
    -0.10
    åĴ«
    -0.09
    çģ¼
    -0.09
    led
    -0.09
    anni
    -0.09
    çĮİ
    -0.09
    çĭ¬ä¸Ģ
    -0.09
    éĢłåŀĭ
    -0.09
    POSITIVE LOGITS
    OTOR
    0.09
    otor
    0.08
     Arrow
    0.08
    æ·¼
    0.08
    nob
    0.08
    вÑĥ
    0.08
    é¢Īéĥ¨
    0.08
    vak
    0.08
    åĮºåĪĨ
    0.08
     dt
    0.08
    Activations Density 0.237%

    No Known Activations