© 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. 36981
    Prev
    Next
    INDEX
    Explanations

    agreement and consensus

    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
    eneg
    -0.09
    åı¸
    -0.09
    æģ£
    -0.08
    æį§
    -0.08
     encounters
    -0.08
    游
    -0.08
    çī¹æĿĥ
    -0.08
    纯
    -0.08
    çħ§å°Ħ
    -0.08
     dens
    -0.08
    POSITIVE LOGITS
    ä¸Ģèĩ´
    0.24
    åħ±è¯Ĩ
    0.22
     agreement
    0.18
     consensus
    0.18
    åIJĮæĦı
    0.17
    绣ä¸Ģ
    0.16
     agreeing
    0.16
    ä¸Ģèĩ´æĢ§
    0.16
    æĦıè§ģ
    0.15
     agree
    0.15
    Activations Density 0.101%

    No Known Activations