© 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. 2038
    Prev
    Next
    INDEX
    Explanations

    game symbols and payouts

    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
     vandal
    -0.26
     civilian
    -0.25
    æĿī
    -0.25
    ros
    -0.24
    泯
    -0.24
    纶
    -0.24
     rational
    -0.23
     dr
    -0.23
    èĭŁ
    -0.23
    public
    -0.23
    POSITIVE LOGITS
    åıłåĬł
    0.28
    触åıij
    0.28
     Symbols
    0.28
     Diamonds
    0.27
     payout
    0.26
    -symbol
    0.26
    æİĴåĪĹ
    0.26
     GOLD
    0.26
    é¢Ŀå¤ĸ
    0.25
     payouts
    0.25
    Activations Density 0.015%

    No Known Activations