© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21436
    Prev
    Next
    INDEX
    Explanations

    epigraph, epigen, epidermis, epics

    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
    AndView
    -0.09
    _endian
    -0.09
    æģ¨ä¸įå¾Ĺ
    -0.08
    ught
    -0.08
    Щ
    -0.08
    جة
    -0.08
    ữ
    -0.08
    iance
    -0.08
    ulton
    -0.08
    ãĥ¼ãĥł
    -0.08
    POSITIVE LOGITS
    èįī
    0.10
    ocale
    0.09
    åıĤè°ĭ
    0.09
    (ep
    0.09
    æĸĹäºī
    0.09
    .ep
    0.09
    èĩªè´Ł
    0.09
    rist
    0.09
    çļĦæĪIJéķ¿
    0.09
     ep
    0.09
    Activations Density 0.026%

    No Known Activations