© 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. 17186
    Prev
    Next
    INDEX
    Explanations

    teachers, educators, union, pay

    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
    éº
    -0.10
    _dimensions
    -0.09
     Gang
    -0.09
    æļ´é£İ
    -0.09
    _LD
    -0.09
    åľ°æ®µ
    -0.09
    nova
    -0.08
    讼
    -0.08
     gang
    -0.08
     Cody
    -0.08
    POSITIVE LOGITS
    åħ¬åĬ¡åijĺ
    0.10
    äºĭä¸ļåįķä½į
    0.10
    åħ¬åĬ¡
    0.09
    ç§ijæķĻ
    0.09
    註
    0.09
    亲åıĭ
    0.09
    é¢Ģ
    0.09
    åĴ¸
    0.09
    èģĮä¸ļ
    0.08
    家å±ŀ
    0.08
    Activations Density 0.021%

    No Known Activations