© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7178
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    ä»İæŃ¤
    -0.09
    让ä»ĸ们
    -0.09
    éŁŃ
    -0.09
    æķŀå¼Ģ
    -0.09
    ä¸ļæĢģ
    -0.08
    å᳿ĺ¯
    -0.08
    0
    -0.08
    å¼ĢåĬŀ
    -0.08
    éĻIJãĤĬ
    -0.08
    POSITIVE LOGITS
    æĺ¨
    0.10
    å¯Ħ
    0.10
    пи
    0.09
    æľįåĬ¡ä¸Ńå¿ĥ
    0.08
    nox
    0.08
    nofollow
    0.08
    éĻŁ
    0.08
    è¿ijæĹ¥
    0.08
    æĺ¨æĻļ
    0.08
    æĦıæĢĿæĺ¯
    0.08
    Activations Density 0.025%

    No Known Activations