© 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. 127
    Prev
    Next
    INDEX
    Explanations

    in-house, own, owned, proprietary

    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
    clud
    -0.28
    éĺĤ
    -0.26
    容纳
    -0.25
    çĪ±ä½ł
    -0.24
    /change
    -0.24
     episode
    -0.24
    è¿®
    -0.23
    éĴ¿
    -0.23
    è®©ä½ł
    -0.22
    ·»
    -0.21
    POSITIVE LOGITS
     proprietary
    0.45
     own
    0.39
    åİŁåĪĽ
    0.39
     própria
    0.32
    èĩªèIJ¥
    0.32
    à¹Ģà¸Ńà¸ĩ
    0.31
    çĭ¬æľīçļĦ
    0.29
    -built
    0.29
     alone
    0.29
     owned
    0.28
    Activations Density 0.071%

    No Known Activations