© 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. 7776
    Prev
    Next
    INDEX
    Explanations

    win over

    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
    èĢĥéªĮ
    -0.10
    æī°
    -0.09
    åĸĤ
    -0.08
     Reb
    -0.08
     smugg
    -0.08
    ãģ±
    -0.08
    åħį
    -0.08
     McMaster
    -0.08
    èħ°
    -0.08
    REN
    -0.08
    POSITIVE LOGITS
    积
    0.09
    èħĬ
    0.09
     nearer
    0.09
    漪
    0.09
    é«ĺå±Ĥ次
    0.09
    主é¢ĺ
    0.08
    å¾Īæĸ¹ä¾¿
    0.08
     tạm
    0.08
    å±ŀäºİèĩªå·±
    0.08
     Tavern
    0.08
    Activations Density 0.021%

    No Known Activations