© 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. 40074
    Prev
    Next
    INDEX
    Explanations

    bil, bilayer, biloba, bilinear

    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
    ../../../
    -0.16
    ../../
    -0.12
    ../../../../
    -0.11
    наÑĤ
    -0.10
    ов
    -0.09
    eer
    -0.09
    nen
    -0.09
    ymm
    -0.09
    ues
    -0.09
    亢
    -0.09
    POSITIVE LOGITS
    istic
    0.10
    hog
    0.09
    icious
    0.08
    èĥĿ
    0.08
    opsy
    0.08
    ä¸įèµ·
    0.08
    åįĩ级æĶ¹éĢł
    0.08
    åĭĥåĭĥ
    0.08
    è¡·
    0.08
    voor
    0.08
    Activations Density 0.009%

    No Known Activations