© 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. 8753
    Prev
    Next
    INDEX
    Explanations

    Hippocampus and Hippodrome

    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
    راد
    -0.10
    ãģ±
    -0.10
     nóng
    -0.09
    acular
    -0.09
     Bol
    -0.09
    ëĤľ
    -0.09
     اÙĦÙĥبرÙī
    -0.08
     luáºŃn
    -0.08
    ìĤ¬íķŃ
    -0.08
    çŃ®
    -0.08
    POSITIVE LOGITS
    essen
    0.10
    æѤå¤ĸ
    0.09
    æĪ®
    0.09
    cal
    0.09
    ically
    0.09
    ç±į
    0.09
    hic
    0.09
    åŃĺéĩı
    0.08
     Moff
    0.08
    esimal
    0.08
    Activations Density 0.004%

    No Known Activations