© 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. 5615
    Prev
    Next
    INDEX
    Explanations

    manifests as

    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
    鬲
    -0.10
    é¢ł
    -0.10
    æľªæĪIJ
    -0.09
    ìŀ¥ìĿĦ
    -0.09
    æ±²
    -0.09
    æĿĢèıĮ
    -0.09
    毳
    -0.09
    avis
    -0.09
    ische
    -0.08
    èĮ¹
    -0.08
    POSITIVE LOGITS
    表çݰ为
    0.17
    表çİ°
    0.15
    ä½ĵçİ°
    0.13
    表çı¾
    0.13
    å½¢å¼ı
    0.13
    ä½ĵçİ°åľ¨
    0.12
     manifestation
    0.12
    å¤ļç§įå½¢å¼ı
    0.11
    åħħåĪĨä½ĵçİ°
    0.11
    ä½ĵçİ°åĩº
    0.11
    Activations Density 0.065%

    No Known Activations