© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8964
    Prev
    Next
    INDEX
    Explanations

    Type or Material specifications

    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
    çĶļèĩ³
    -0.10
    ams
    -0.09
    ritable
    -0.09
    橱
    -0.09
    çĬ¯
    -0.09
    çĿĢçľ¼
    -0.08
    å°ı康社ä¼ļ
    -0.08
    nis
    -0.08
    fish
    -0.08
    æīĵåĵį
    -0.08
    POSITIVE LOGITS
    éĩįéĩı
    0.10
    çī¹å¾ģ
    0.09
     Exclusive
    0.09
     Features
    0.08
    æľīæīĢ
    0.08
    æ·¨
    0.08
     features
    0.08
    æŃ£å¸¸ä½¿çĶ¨
    0.08
     Daly
    0.08
    é¡ı
    0.08
    Activations Density 0.027%

    No Known Activations