© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35740
    Prev
    Next
    INDEX
    Explanations

    quoted words or phrases

    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
    ä¸Ģæīĭ
    -0.09
    çļĦçĶŁåij½
    -0.08
    路桥
    -0.08
    еÑĢж
    -0.08
    jour
    -0.08
    æĵĶ
    -0.08
    è¿ijä¸īå¹´
    -0.08
    ubi
    -0.08
    éĶĹ
    -0.08
    TOT
    -0.08
    POSITIVE LOGITS
    æīĢè°ĵ
    0.12
    æīĢè°ĵçļĦ
    0.12
     supposed
    0.10
     purported
    0.09
     allegedly
    0.09
     supposedly
    0.09
    ribbon
    0.09
    è¦ģçĶ¨
    0.09
     “
    0.08
    é¹Ĺ
    0.08
    Activations Density 0.083%

    No Known Activations