© 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. 29713
    Prev
    Next
    INDEX
    Explanations

    SharePoint workflow document

    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
    娩
    -0.10
    dsl
    -0.09
    ager
    -0.09
    ivas
    -0.09
    usk
    -0.09
    stab
    -0.09
    æŁ´
    -0.09
    ç¥ļ
    -0.09
    åѦçĶŁçļĦ
    -0.09
    å¼
    -0.09
    POSITIVE LOGITS
     SharePoint
    0.11
    åħħæĸ¥
    0.10
    èĥĸåŃIJ
    0.09
    央ä¼ģ
    0.09
    çĶ¨æīĭ
    0.09
    pol
    0.08
    æ¯ı人
    0.08
    åĽ½èµĦå§Ķ
    0.08
    çĻ¾ç§ij
    0.08
     NodeType
    0.08
    Activations Density 0.125%

    No Known Activations