© 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. 34238
    Prev
    Next
    INDEX
    Explanations

    nationalities, professions, places

    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§īå¾Ĺå¾Ī
    -0.11
    çī¹åĪ«
    -0.10
    åĪĽä¸ļèĢħ
    -0.10
    çľĭæĿ¥
    -0.10
    ä¸Ģ个å°ı
    -0.10
    çī¹åĪ¥
    -0.09
    æĢ§å¼º
    -0.09
    éĩįçĤ¹åħ³æ³¨
    -0.09
    çī¹æ®ĬæĥħåĨµ
    -0.09
    OwnerId
    -0.09
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.09
    èĪĮ
    0.09
    åľ°æ®µ
    0.08
     педагог
    0.08
     Hel
    0.08
    èij©
    0.08
     ulus
    0.08
    åľ°æłĩ
    0.08
    èİ«è¿ĩäºİ
    0.08
    çĿģå¼Ģ
    0.08
    Activations Density 0.149%

    No Known Activations