© 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. 37356
    Prev
    Next
    INDEX
    Explanations

    peek at, peek underneath

    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
    大ä¼Ĺ
    -0.09
    sWith
    -0.08
    รà¸Ńà¸ĩ
    -0.08
    naire
    -0.08
    иÑĪ
    -0.08
    ابÙĦ
    -0.08
    ainter
    -0.07
    å¤§éĽ¨
    -0.07
     gist
    -0.07
    æłĩ
    -0.07
    POSITIVE LOGITS
    holes
    0.12
    å±±åİ¿
    0.10
    íķĢ
    0.10
    æīĭèĦļ
    0.09
     holes
    0.09
     ÑĢÑĥк
    0.09
    åĩºãģĹ
    0.09
    è¿ĻéĩĮçļĦ
    0.09
    褶
    0.09
    hole
    0.09
    Activations Density 0.003%

    No Known Activations