© 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. 232
    Prev
    Next
    INDEX
    Explanations

    sports team names

    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
    åĴĮæľįåĬ¡
    -0.23
    è¿Ļ个æĹ¶ä»£
    -0.23
    该æĿij
    -0.23
    èµĺ
    -0.23
    æ°ijçĶ¨
    -0.23
    为广大
    -0.23
    åİ©
    -0.23
    å¾Ģå¹´
    -0.22
    该项
    -0.22
    _checks
    -0.22
    POSITIVE LOGITS
     bree
    0.26
     recoil
    0.24
    Sounds
    0.24
    supply
    0.24
    继ç»Ńä¿ĿæĮģ
    0.23
    innen
    0.23
    éĤ£è¾¹
    0.23
    åıįåĩ»
    0.22
    å¾ĹåĪĨ
    0.22
    Sci
    0.22
    Activations Density 0.012%

    No Known Activations