© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51847
    Prev
    Next
    INDEX
    Explanations

    gambling and financial decisions

    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
    æĺ¯ä¸įåı¯èĥ½
    -0.09
     Ñģка
    -0.09
    ään
    -0.09
    -corner
    -0.09
     ÑĢаÑģÑģмаÑĤÑĢ
    -0.09
    害
    -0.09
    çĥ¦
    -0.09
    çĽ¸äº²
    -0.08
     Mature
    -0.08
    achs
    -0.08
    POSITIVE LOGITS
     gamb
    0.12
    çŃĸçķ¥
    0.12
     gamble
    0.11
    åĨ³çŃĸ
    0.11
    æĹ¶æľº
    0.10
    æĺ§
    0.10
    åįļå¼Ī
    0.10
    大èĥĨ
    0.10
    åĨĴçĿĢ
    0.10
    æķ¢äºİ
    0.10
    Activations Density 0.181%

    No Known Activations