© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47402
    Prev
    Next
    INDEX
    Explanations

    now controlling busnow in silencenow changingnow goingnow installed

    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
    Negative Logits
    临
    -0.09
    athe
    -0.09
    Normals
    -0.08
     иÑģкÑĥÑģ
    -0.08
    ãģķãģĪ
    -0.08
    orsch
    -0.08
    stadt
    -0.08
    à¦Ń
    -0.08
    æī¶
    -0.08
    èĩ³ä»Ĭ
    -0.08
    POSITIVE LOGITS
    è¿ĻæŶ
    0.14
    è¿ĻæŶåĢĻ
    0.14
    æѤæŶ
    0.13
    åıĺå¾Ĺ
    0.13
    ä»ĸå·²ç»ı
    0.11
    æѤæĻĤ
    0.11
    æѤåĪ»
    0.10
    è¿Ļ个æŶåĢĻ
    0.10
    第ä¸ī次
    0.10
    å·²ç»ıæľī
    0.10
    Activations Density 0.041%

    No Known Activations