© 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. 27176
    Prev
    Next
    INDEX
    Explanations

    in case

    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
    è§ļ
    -0.09
    å¦Ĥæŀľä¸įæĺ¯
    -0.09
    足
    -0.09
    å¿ħçĦ¶ä¼ļ
    -0.09
    ä¸įåı¯èĥ½
    -0.09
    å§ij
    -0.09
    æľĢéļ¾
    -0.09
     Bez
    -0.09
    ìłĦ문
    -0.09
    åħ¶å®ŀ
    -0.08
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.15
    wards
    0.09
     accompl
    0.09
    æľīä¸Ģ天
    0.09
    akin
    0.09
    æľī人
    0.09
    mare
    0.08
    ãĤ·ãĤ¢
    0.08
     someone
    0.08
     lẫn
    0.08
    Activations Density 0.010%

    No Known Activations