© 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. 4498
    Prev
    Next
    INDEX
    Explanations

    occupational fame and salary

    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
    å·²ç»ıæľīäºĨ
    -0.10
    è¿Łè¿Ł
    -0.09
    ä¸ĵ家ç»Ħ
    -0.09
    _pad
    -0.09
    å·²ç»ıåľ¨
    -0.08
    éĴĪ
    -0.08
    _MINOR
    -0.08
    æ¸İ
    -0.08
    coon
    -0.08
    åĬ¿å¤´
    -0.08
    POSITIVE LOGITS
    é£İ鼨
    0.10
    é£İåIJ¹
    0.10
    å·¥ä½ľ
    0.10
    åѤçĭ¬
    0.10
    é»ĺé»ĺ
    0.09
     glamorous
    0.09
    èĩªå¾ĭ
    0.09
    é«ĺ强度
    0.09
    ç´«å¤ĸ线
    0.09
    åįķè°ĥ
    0.09
    Activations Density 0.088%

    No Known Activations