© 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. 7723
    Prev
    Next
    INDEX
    Explanations

    so far

    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
    ä¹ŁæĽ¾
    -0.10
    æĪijå½ĵæŶ
    -0.10
    æĪIJé¾Ļ
    -0.09
    æĽ¾ä»»
    -0.09
    贯穿
    -0.09
    æĽ¾åľ¨
    -0.09
    æĽ¾
    -0.09
    èĢģæŧ
    -0.08
    éĿ¢
    -0.08
    .Face
    -0.08
    POSITIVE LOGITS
    çľĭæĿ¥
    0.11
    åĪĿæŃ¥
    0.10
    缮åīį为æŃ¢
    0.10
    è¿Ħä»Ĭ为æŃ¢
    0.09
    å´Ń
    0.09
    tent
    0.09
     пока
    0.09
    æŃ£åľ¨è¿Ľè¡Į
    0.09
    å·²ç»ıå¼Ģå§ĭ
    0.09
    ibs
    0.09
    Activations Density 0.060%

    No Known Activations