© 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. 17596
    Prev
    Next
    INDEX
    Explanations

    sugar, sucrose, cane

    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
    çĭIJ
    -0.10
    羿
    -0.09
     половин
    -0.09
    è¥Ł
    -0.09
     Ying
    -0.09
    æĺ¯ä¸Ģ件
    -0.08
    çĿ¢
    -0.08
    å®°
    -0.08
    Chrome
    -0.08
    ç³ł
    -0.08
    POSITIVE LOGITS
    èĪŀ
    0.10
    ahir
    0.10
    æĮ½
    0.09
    ç³ĸ
    0.09
    æĤŁ
    0.08
    VOKE
    0.08
    çļİ
    0.08
     freder
    0.08
    åij¨æľŁ
    0.08
    åIJĦåĽ½
    0.08
    Activations Density 0.024%

    No Known Activations