© 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. 52436
    Prev
    Next
    INDEX
    Explanations

    perceiving or distinguishing

    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
    ä¹Łæľīä¸ĢäºĽ
    -0.10
    æ±ŁåĮĹ
    -0.09
    åIJĦè¡Į
    -0.09
    zig
    -0.09
    ercul
    -0.09
    åĨ¶
    -0.09
    éļıæŶéļıåľ°
    -0.09
    ä¸įæŃ¢
    -0.09
    ographed
    -0.08
    ä¸įåłª
    -0.08
    POSITIVE LOGITS
    å¯Łè§ī
    0.16
    çľĭä¸įåĩº
    0.15
    çľĭä¸įè§ģ
    0.14
    ä¸įå½±åĵį
    0.12
    çľĭä¸įåĪ°
    0.12
    æĹłç¼Ŀ
    0.11
    è§ī
    0.11
     unnoticed
    0.11
    åŀ¸
    0.11
    ç²
    0.10
    Activations Density 0.065%

    No Known Activations