© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7481
    Prev
    Next
    INDEX
    Explanations

    key members, moments, conservatives, players, House, Senate, function

    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
    æ¶Ł
    -0.11
    饶
    -0.09
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.09
    ä»»ä½ķå½¢å¼ı
    -0.09
    é¥
    -0.09
    æĸ°å½¢åĬ¿
    -0.08
    ä¸ĢèĪ¬çļĦ
    -0.08
     Ket
    -0.08
    åħĨ
    -0.08
     lÃłnh
    -0.08
    POSITIVE LOGITS
    ä¸įåİ»
    0.10
    çļĦ人çĶŁ
    0.10
    ä¸įä½ı
    0.09
    criptive
    0.09
    æŀ¶åŃIJ
    0.09
    åľĪåŃIJ
    0.09
    adr
    0.08
     crucial
    0.08
    æĺ§
    0.08
    çļĦéĩįè¦ģ
    0.08
    Activations Density 0.073%

    No Known Activations