© 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. 60786
    Prev
    Next
    INDEX
    Explanations

    HTML tag `<head>`

    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
    tl
    -0.09
    æĽ´è¦ģ
    -0.08
     lash
    -0.08
    ease
    -0.08
    å¾Ĺèµ·
    -0.08
    èĬĤ
    -0.08
    uos
    -0.08
     lust
    -0.08
    e
    -0.08
    ecc
    -0.07
    POSITIVE LOGITS
    缤
    0.10
    elic
    0.10
    ãģıãĤĵ
    0.09
    pé
    0.09
    quo
    0.08
    ä¸į太好
    0.08
    terior
    0.08
    ä¸Ģåľº
    0.08
    comings
    0.08
    å·²ä¹ħçļĦ
    0.08
    Activations Density 0.032%

    No Known Activations