© 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. 59451
    Prev
    Next
    INDEX
    Explanations

    constitutional referendum

    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
    ened
    -0.10
    ties
    -0.09
    à¹Ģหà¸Ļ
    -0.09
     duro
    -0.09
    ness
    -0.09
    ening
    -0.09
    itude
    -0.08
    ìķł
    -0.08
    å°º
    -0.08
     sider
    -0.08
    POSITIVE LOGITS
    寿
    0.10
    isz
    0.10
    ally
    0.09
     opinión
    0.09
    orris
    0.09
    峦
    0.09
    icular
    0.09
    able
    0.09
    泡泡
    0.08
    å®ļäºĨ
    0.08
    Activations Density 0.005%

    No Known Activations