© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15915
    Prev
    Next
    INDEX
    Explanations

    class reunion alumni

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    å©¢
    -0.20
    仨
    -0.20
    å·´æĭī
    -0.20
    å¹²é¢Ħ
    -0.20
    æĬ¼
    -0.19
    çī¹ä»·
    -0.19
    urgent
    -0.19
    ï·º
    -0.19
    åĩĢ
    -0.18
    æŀĦçŃij
    -0.18
    POSITIVE LOGITS
    æ¯įæł¡
    0.33
    æł¡åıĭ
    0.33
     alumni
    0.32
     Alumni
    0.31
     reunion
    0.27
    æ¯ķä¸ļåIJİ
    0.27
    å½ĵå¹´
    0.26
    æĢĢ念
    0.25
    æŶåħī
    0.24
    çķĻåľ¨
    0.23
    Activations Density 0.036%

    No Known Activations