© 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. 27099
    Prev
    Next
    INDEX
    Explanations

    unexpected positive emotion

    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
    弦
    -0.09
    太å°ij
    -0.09
    ä¸ĭåİ»
    -0.09
    æľ¬æ¬¡æ´»åĬ¨
    -0.09
    嵬
    -0.09
    _DOM
    -0.09
    amic
    -0.08
    è¹ļ
    -0.08
    è´¨åľ°
    -0.08
    äºĨä¸ĭæĿ¥
    -0.08
    POSITIVE LOGITS
    没æĥ³åĪ°
    0.16
    æĥĬåĸľ
    0.16
    没æľīæĥ³åĪ°
    0.14
     surprise
    0.14
    æĦıå¤ĸ
    0.13
    æĥĬå¥ĩ
    0.13
    åį´åıijçİ°
    0.13
    åıijçİ°
    0.12
     surprised
    0.11
     surprises
    0.11
    Activations Density 0.048%

    No Known Activations