© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62135
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory compliance

    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
    ä¸įè¦ģåĨį
    -0.11
    çľĭæ¸ħ
    -0.11
    解å¼Ģ
    -0.10
    èĪIJ
    -0.09
    æľĢ好ä¸įè¦ģ
    -0.09
    ä¸įè¦ģ
    -0.09
    顺便
    -0.09
    å½±åĵįåĬĽçļĦ
    -0.09
    .removeAttribute
    -0.09
    æľįåĬ¡èĥ½åĬĽ
    -0.09
    POSITIVE LOGITS
    æݪæĸ½
    0.14
    å®ļæľŁ
    0.12
    åĪ¶å®ļäºĨ
    0.11
    ä¸¥æł¼èIJ½å®ŀ
    0.11
     internal
    0.10
    æ¯ıå¹´éĥ½
    0.10
    严å¯Ĩ
    0.10
    åĨħéĥ¨
    0.10
    åħ¨åijĺ
    0.10
    åļ´
    0.10
    Activations Density 0.081%

    No Known Activations