© 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. 8166
    Prev
    Next
    INDEX
    Explanations

    so [adjective/adverb]

    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
     ÑĥпÑĢав
    -0.09
    amac
    -0.09
    æĭŁå®ļ
    -0.08
    æħ°
    -0.08
     Ùħج
    -0.08
    lia
    -0.08
     quanto
    -0.08
    è°¦
    -0.08
    éĽħ
    -0.08
    .bl
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Īå¤ļ
    0.15
    å¦ĤæѤ
    0.14
    è¿Ļä¹Īä¹ħ
    0.13
    è¿Ļä¹Ī大
    0.13
    éĤ£ä¹Īå¤ļ
    0.13
    è¿Ļä¹Ī
    0.12
    éĢĻ麼
    0.12
    è¿Ļç§įæĸ¹å¼ı
    0.12
    éĤ£ä¹Ī
    0.11
    è¿ĻèĪ¬
    0.11
    Activations Density 0.018%

    No Known Activations