© 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. 512
    Prev
    Next
    INDEX
    Explanations

    agreement terms, conditions, or stipulations

    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
    让åѦçĶŁ
    -0.26
    让人们
    -0.25
     folk
    -0.25
     often
    -0.25
     websites
    -0.25
     criminals
    -0.24
    罪
    -0.24
     brilliantly
    -0.24
     folks
    -0.23
    çīĩåĪ»
    -0.23
    POSITIVE LOGITS
    å±ĬæŶ
    0.45
    约å®ļ
    0.45
     agreed
    0.44
    çĶ²æĸ¹
    0.38
     future
    0.37
     agreement
    0.36
     renegot
    0.36
    æĿ¡æ¬¾
    0.35
    åįıè®®
    0.35
    履约
    0.35
    Activations Density 0.051%

    No Known Activations