© 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. 59321
    Prev
    Next
    INDEX
    Explanations

    check out the

    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
    表æĢģ
    -0.08
    atter
    -0.08
    ValuePair
    -0.08
     lt
    -0.08
    ÑĪе
    -0.08
    纷
    -0.08
    iran
    -0.08
    æĹħ游度åģĩ
    -0.08
    泪水
    -0.08
    èĥĮ
    -0.08
    POSITIVE LOGITS
    abit
    0.10
    åĪĨ解
    0.09
    abant
    0.09
    rott
    0.09
    ulary
    0.09
    çļĦä¸ĢéĿ¢
    0.09
    åģ¶çĦ¶
    0.09
    _SS
    0.08
    ibrated
    0.08
    uco
    0.08
    Activations Density 0.013%

    No Known Activations