© 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. 10850
    Prev
    Next
    INDEX
    Explanations

    explaining how something

    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
    åī¡
    -0.09
    人士
    -0.09
    oon
    -0.09
    ãģ£ãģ¦ãĤĭ
    -0.08
    onna
    -0.08
    åľ¨éĤ£éĩĮ
    -0.08
    aris
    -0.08
    çļĦä¸ľè¥¿
    -0.08
    çļĦéĤ£ä¸ª
    -0.08
    rase
    -0.08
    POSITIVE LOGITS
    ä¸įä¹ı
    0.09
    è¯
    0.08
    WARE
    0.08
    kek
    0.08
    åıĤä¸İåĪ°
    0.08
    èį¥
    0.08
     ft
    0.08
    kel
    0.07
    ft
    0.07
    æĥ
    0.07
    Activations Density 1.724%

    No Known Activations