© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 133
    Prev
    Next
    INDEX
    Explanations

    relative pronouns introducing clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    åħĭæľį
    -0.30
    延éķ¿
    -0.24
    贯穿
    -0.24
    æŃ¤æ¬¡
    -0.24
    æŀĦ建
    -0.23
    ä»»ä½ķæŶåĢĻ
    -0.23
    çłĶ究
    -0.23
    继ç»Ń
    -0.23
     michael
    -0.22
    åĬłä¸Ĭ
    -0.22
    POSITIVE LOGITS
     previously
    0.38
     Previously
    0.36
     already
    0.29
     supposedly
    0.27
    åľ¨å¤ĸéĿ¢
    0.27
     formerly
    0.26
     supposed
    0.26
    viously
    0.26
    already
    0.26
     originally
    0.25
    Activations Density 0.175%

    No Known Activations