© 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. 36947
    Prev
    Next
    INDEX
    Explanations

    baby shower, party, gift, registry

    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
    ç½ķ
    -0.09
    1
    -0.09
    åį°
    -0.08
    2
    -0.08
    6
    -0.08
    orn
    -0.08
     Advocate
    -0.08
    5
    -0.08
    8
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    æģŃåĸľ
    0.11
    礼çī©
    0.11
    礼åĵģ
    0.10
    æľįåĬ¡èĥ½åĬĽ
    0.10
    ạng
    0.10
    çŃ¹å¤ĩ
    0.10
     занÑıÑĤ
    0.09
    nestjs
    0.09
    åIJĦä½į
    0.09
    ÙĤد
    0.09
    Activations Density 0.007%

    No Known Activations