© 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. 8339
    Prev
    Next
    INDEX
    Explanations

    Office of the

    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
    zer
    -0.08
    ank
    -0.08
    -0.08
     andre
    -0.08
    eam
    -0.08
    çļĦä¸Ģç§į
    -0.07
     fast
    -0.07
    izon
    -0.07
    è¿ĩäºĨ
    -0.07
    edin
    -0.07
    POSITIVE LOGITS
    åķ¬
    0.10
    åĤ¬
    0.10
    ivities
    0.10
    ä¿Ŀå®ī
    0.10
    ç»ĺ
    0.09
    æ´Ĵ
    0.09
    ä¸Ģç«Ļå¼ı
    0.09
    注æĺİåĩºå¤Ħ
    0.09
    éĹ³
    0.09
    ÑĤен
    0.09
    Activations Density 0.031%

    No Known Activations