© 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. 26087
    Prev
    Next
    INDEX
    Explanations

    emotions and sincerity

    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
    èĢģ大
    -0.09
    thumbs
    -0.09
    æĵį
    -0.09
    ëĭī
    -0.09
    à¸Ńà¸Ļ
    -0.08
    cao
    -0.08
     incon
    -0.08
    _poll
    -0.08
    urses
    -0.08
    _ALIGN
    -0.08
    POSITIVE LOGITS
    æĥħæĦŁ
    0.17
    çļĦæĥħæĦŁ
    0.16
    çļĦæĦŁæĥħ
    0.14
    羣æĥħ
    0.14
    ç»Ĩèħ»
    0.14
    亲æĥħ
    0.13
    æĦŁæĥħ
    0.13
     emotion
    0.12
     emotions
    0.12
    æĦŁäºº
    0.11
    Activations Density 0.102%

    No Known Activations