© 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. 36993
    Prev
    Next
    INDEX
    Explanations

    explaining a definition

    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
    åŃĹ第
    -0.10
    æīĵçĿĢ
    -0.10
    ëį°
    -0.09
     ведÑĮ
    -0.09
    ä¸įèµ·
    -0.08
    owering
    -0.08
    çļĦç¡®
    -0.08
     cháy
    -0.08
    å¦Ļ
    -0.08
    åŁºå»º
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.10
    fully
    0.09
    ä½łèĥ½
    0.09
    ame
    0.09
    å«Ķ
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    å®ĥåı¯ä»¥
    0.08
    çĺĹ
    0.08
    amon
    0.08
    åįģä¸ĩ
    0.08
    Activations Density 0.010%

    No Known Activations