© 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. 19430
    Prev
    Next
    INDEX
    Explanations

    separating clauses or phrases

    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
    åŀĤ
    -0.09
    ä¹Łæľīä¸ĢäºĽ
    -0.09
    ç´ł
    -0.09
    çĬĬ
    -0.08
    械
    -0.08
    aim
    -0.08
    约ä¼ļ
    -0.08
    ä¹Łæľīå¾Īå¤ļ
    -0.08
    achten
    -0.08
    çŃī缸åħ³
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³æĺ¯
    0.11
    çĶļèĩ³
    0.11
    ä¹ĥèĩ³
    0.10
    æĪĸèĢħ说
    0.10
     tháºŃm
    0.09
    æĹħéĢĶ
    0.09
    thon
    0.09
    æĺ¯æĪij们
    0.09
    建ç«ĭèµ·
    0.09
    èĢĮ对äºİ
    0.09
    Activations Density 0.114%

    No Known Activations