© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1888
    Prev
    Next
    INDEX
    Explanations

    streak of wins or losses

    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
    o
    -0.25
    phot
    -0.24
     cooper
    -0.24
    fully
    -0.24
    ä¸Ģé¢Ĺ
    -0.23
    plate
    -0.23
     donated
    -0.23
    lobal
    -0.22
    ialog
    -0.22
    æĵħ
    -0.22
    POSITIVE LOGITS
    æĪIJåĬŁçİĩ
    0.30
    ç»Łè®¡æķ°æį®
    0.29
     statist
    0.29
     losers
    0.27
    çļĦè¶ĭåĬ¿
    0.26
    ç»Łè®¡
    0.26
    åįłæ¯Ķ
    0.26
    åĬ£åĬ¿
    0.25
    人次
    0.25
     statistically
    0.25
    Activations Density 0.008%

    No Known Activations