© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38851
    Prev
    Next
    INDEX
    Explanations

    games, casinos, gambling

    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
    éĤ´
    -0.10
     Ner
    -0.09
    ç»ļ
    -0.09
     ÑģÑĤоÑĢ
    -0.09
    æĭĶ
    -0.09
    åĬĽæ±Ĥ
    -0.08
    æѤæĸĩ
    -0.08
    è§IJ
    -0.08
    æĸ¹åľĨ
    -0.08
    Ứ
    -0.08
    POSITIVE LOGITS
    å¸Ń
    0.10
    å¥ī
    0.10
    é¼ĵ
    0.09
    èħ°
    0.09
    rap
    0.09
    åĮ¡
    0.09
    æĭīæĸ¯
    0.09
    人群
    0.08
     Holt
    0.08
    iera
    0.08
    Activations Density 0.028%

    No Known Activations