© 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. 51980
    Prev
    Next
    INDEX
    Explanations

    incentives and contracts

    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
    æģ¢å¤į
    -0.10
    åŃ£èĬĤ
    -0.09
    åĮ®
    -0.09
    æľªç»ı
    -0.09
     Moment
    -0.08
     Mall
    -0.08
    è¿ĺåİŁ
    -0.08
    ä¸įåħį
    -0.08
    éĶ¦ç»£
    -0.08
    çĸ±
    -0.08
    POSITIVE LOGITS
    æ¿ĢåĬ±
    0.12
    åı²ä¸ĬæľĢ
    0.09
    .pub
    0.08
    åĽļ
    0.08
    çįİ
    0.08
     chặt
    0.08
    ç½ķè§ģ
    0.08
    æ¥Ķ
    0.08
     Priest
    0.08
    çĶĦ
    0.08
    Activations Density 0.123%

    No Known Activations