© 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. 36855
    Prev
    Next
    INDEX
    Explanations

    explaining filtering remembering assistance

    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
    æĽ´å¥½çļĦ
    -0.10
    主è¦ģä»İäºĭ
    -0.10
    åįģåĪĨ
    -0.09
    æľīæĽ´å¥½çļĦ
    -0.09
    inheritDoc
    -0.09
     Middleton
    -0.09
    dit
    -0.09
    ä¸įæħİ
    -0.09
     Dit
    -0.09
    éĿŀ常é«ĺ
    -0.09
    POSITIVE LOGITS
    é¢ĦæľŁ
    0.09
    ç¿ķ
    0.09
    illac
    0.08
    åĿıäºĭ
    0.08
    æľŁåĨħ
    0.08
    èĩªèº«
    0.08
     ISC
    0.08
    assy
    0.08
    oted
    0.08
    å¼ĢåĪĽ
    0.08
    Activations Density 0.043%

    No Known Activations