© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7234
    Prev
    Next
    INDEX
    Explanations

    technical terms and abbreviations

    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
    æľ¦èĥ§
    -0.09
     Hastings
    -0.08
    éĸī
    -0.08
     remotely
    -0.08
    ä¼ı
    -0.08
    éĹŃ
    -0.08
    ild
    -0.08
    bury
    -0.08
    æľº
    -0.08
    outu
    -0.08
    POSITIVE LOGITS
    çĶ·äºº
    0.09
    PHY
    0.09
    æŃ¤äºº
    0.09
    çĭ¬ç«ĭ
    0.09
     Zucker
    0.09
    çĺ¦
    0.09
    ä¸Ģ份
    0.09
    æŶæĬ¥
    0.09
    atics
    0.08
    ä¸ĵè¾ij
    0.08
    Activations Density 0.004%

    No Known Activations