© 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. 61634
    Prev
    Next
    INDEX
    Explanations

    organizations founded

    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
    æ´Ħ
    -0.11
    æĴŀ
    -0.10
    çľĭä½ł
    -0.10
    ä»İåݻ年
    -0.10
    ÑĤоп
    -0.09
    èĤĩ
    -0.09
    æijĦ
    -0.09
    对å¾ħ
    -0.09
    acent
    -0.09
    æīĵçIJĥ
    -0.09
    POSITIVE LOGITS
    æĪIJ为
    0.11
    æĪIJçĤº
    0.10
    æĪIJ为ä¸Ģ个
    0.10
    æĪIJ为äºĨ
    0.09
    ä¸Ģ缴
    0.09
     became
    0.09
     become
    0.09
    跻身
    0.09
    å·²æĪIJ为
    0.09
    å·²ç»ıæĪIJ为
    0.08
    Activations Density 0.094%

    No Known Activations