© 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. 56194
    Prev
    Next
    INDEX
    Explanations

    written by

    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
    ãģĹãģ¦ãģĬãģı
    -0.11
    ä¸ĭåİ»
    -0.10
    å·¥åķĨ
    -0.10
    ainers
    -0.09
    æ£ĭçīĮ
    -0.09
    oppers
    -0.09
     tÃł
    -0.09
    콤
    -0.09
    ROUT
    -0.09
    å°ıç¼ĸ
    -0.09
    POSITIVE LOGITS
    å¤ļç§įå½¢å¼ı
    0.09
    UCT
    0.08
    åĸ»
    0.08
    æݥ管
    0.08
    æīĭåĬ¿
    0.08
    åı£ä¸Ń
    0.08
    _MUT
    0.08
    ä½ıæīĢ
    0.08
    èĬ¦
    0.08
    趣
    0.08
    Activations Density 0.364%

    No Known Activations