© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 506
    Prev
    Next
    INDEX
    Explanations

    money owed or due

    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
    æľīåĬ©äºİ
    -0.28
    æľĢ大ç¨ĭ度
    -0.25
     dummy
    -0.23
    离ä¸įå¼Ģ
    -0.23
    å¤ļæł·æĢ§
    -0.23
     twink
    -0.22
    çŃĸ
    -0.22
    FEATURE
    -0.22
    çģµæĦŁ
    -0.22
    æ©
    -0.22
    POSITIVE LOGITS
     owed
    0.48
     overdue
    0.36
     accrued
    0.36
    æĭĸæ¬ł
    0.35
     dues
    0.34
    ä¹īåĬ¡
    0.33
     obligations
    0.33
    æ¬ł
    0.31
    æķ°é¢Ŀ
    0.31
     amounts
    0.31
    Activations Density 0.032%

    No Known Activations