© 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. 839
    Prev
    Next
    INDEX
    Explanations

    start to finish

    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
    rozen
    -0.10
    lox
    -0.10
    YST
    -0.10
    群
    -0.09
    大åŀĭ
    -0.09
    ä»»
    -0.09
     Hoy
    -0.09
    .staff
    -0.09
     Erect
    -0.09
    å·¢
    -0.09
    POSITIVE LOGITS
    åħ¨æµģç¨ĭ
    0.11
     entire
    0.11
    åīįåIJİ
    0.10
     entirety
    0.10
    ä¸Ģ缴åĪ°
    0.10
     throughout
    0.10
    ä¸Ĭä¸ĭ
    0.09
    åħ¨è¿ĩç¨ĭ
    0.09
    åħ¨ç¨ĭ
    0.09
    åĪ°æľĢåIJİ
    0.09
    Activations Density 0.040%

    No Known Activations