© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52769
    Prev
    Next
    INDEX
    Explanations

    plural nouns referencing categories or items

    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
    ä¼łç»Ł
    -0.10
     Fab
    -0.10
    Fab
    -0.10
    åºĨ幸
    -0.09
    oder
    -0.08
    cow
    -0.08
    ube
    -0.08
    å¾Ģä¸ĭ
    -0.08
     какие
    -0.08
    otti
    -0.08
    POSITIVE LOGITS
     Sever
    0.11
    èĬ¹
    0.10
    ROUT
    0.08
    .ErrorMessage
    0.08
    éŃĦ
    0.08
    æģ¬
    0.08
    paced
    0.08
    è¹Ĭ
    0.08
    èĩªåĪ¶
    0.08
    Edited
    0.08
    Activations Density 0.237%

    No Known Activations