© 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. 9093
    Prev
    Next
    INDEX
    Explanations

    arcade and Atari games

    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
    ened
    -0.09
    lessly
    -0.09
    çĨı
    -0.09
    ç»
    -0.09
    ning
    -0.08
    çĩ®
    -0.08
    ëĦ
    -0.08
    ening
    -0.08
    åĵģçīĮ形象
    -0.08
    èħĪ
    -0.08
    POSITIVE LOGITS
    onne
    0.11
    æ¿ij
    0.09
    éĴ¿
    0.09
    à¹Ģà¸ĸ
    0.09
    icular
    0.09
    æĽĻåħī
    0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.09
    Reporter
    0.09
    onis
    0.08
     дог
    0.08
    Activations Density 0.004%

    No Known Activations