© 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. 8622
    Prev
    Next
    INDEX
    Explanations

    event completion or state change

    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
    æ·¦
    -0.12
    鹧
    -0.09
    éĵł
    -0.09
    è¯ĺ
    -0.09
    è½»æĿ¾
    -0.09
    以åIJİ
    -0.09
    æ¸İ
    -0.08
    é¢ijé¢ij
    -0.08
    IDA
    -0.08
    ä¸įèµ·
    -0.08
    POSITIVE LOGITS
    éĤ£è¾¹
    0.10
    å¹³å®ī
    0.09
    IVES
    0.09
    å·²åľ¨
    0.09
    iem
    0.09
     ÑģамоÑģÑĤоÑı
    0.09
    ester
    0.08
    已被
    0.08
    Chess
    0.08
    æĭĺçķĻ
    0.08
    Activations Density 0.069%

    No Known Activations