© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58944
    Prev
    Next
    INDEX
    Explanations

    Sean followed by surname or initial

    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
    ä¸įäºĨ
    -0.13
    ĸ
    -0.09
    онÑĤ
    -0.09
    ous
    -0.08
    çĦ¶æĺ¯
    -0.08
    ë¥ł
    -0.08
    ached
    -0.08
    ixon
    -0.08
    壤
    -0.07
    éĻIJæľŁ
    -0.07
    POSITIVE LOGITS
    ingly
    0.14
    ingle
    0.10
    sville
    0.09
    èĥ½å¾ĹåĪ°
    0.09
    çľĭçľĭ
    0.09
    çī¹åĪ«æĺ¯
    0.09
    adin
    0.09
    parency
    0.09
    .Locale
    0.09
    âĢĹ
    0.09
    Activations Density 0.038%

    No Known Activations