© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10082
    Prev
    Next
    INDEX
    Explanations

    gambling and gamblers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    å¸ĸ
    -0.10
    åī²
    -0.10
    rack
    -0.09
    åħ¥åĽŃ
    -0.09
    ulton
    -0.09
    æ¹¾åĮº
    -0.09
    å½ķ
    -0.08
    èĮĢ
    -0.08
    yar
    -0.08
    裱
    -0.08
    POSITIVE LOGITS
    èµĮåįļ
    0.18
    骰
    0.16
    èµĮ
    0.16
    ðŁİ²
    0.15
     Gambling
    0.15
     dice
    0.14
    麻å°Ĩ
    0.14
     gambling
    0.14
    èĢģèĻİæľº
    0.14
    gam
    0.13
    Activations Density 0.069%

    No Known Activations