© 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. 37175
    Prev
    Next
    INDEX
    Explanations

    butter and related concepts

    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
    oping
    -0.10
    itzer
    -0.10
    ä¹ĭåĨħ
    -0.10
    andre
    -0.09
    ÑĥÑī
    -0.09
    æ½ĩæ´Ĵ
    -0.09
    stead
    -0.09
    åĨĮ
    -0.09
    è¿ĩ大
    -0.09
    纲
    -0.08
    POSITIVE LOGITS
    ongs
    0.10
    åĿĬ
    0.09
    flies
    0.09
    fly
    0.09
    cream
    0.09
    ong
    0.09
    craft
    0.09
    åİŁæĸĩ
    0.08
    毫ä¸į
    0.08
    æ°ijå¿ĥ
    0.08
    Activations Density 0.009%

    No Known Activations