© 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
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12280
    Prev
    Next
    INDEX
    Explanations

    activity/event naming

    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
    è£ħä¿®
    -0.21
    æĹłæīĢ
    -0.20
    è°Īè¯Ŀ
    -0.20
    blings
    -0.20
    æīĵ交éģĵ
    -0.19
     flor
    -0.19
    è°¯
    -0.19
    åģ¶å°Ķ
    -0.18
     content
    -0.18
     rico
    -0.18
    POSITIVE LOGITS
    åıĤä¸İèĢħ
    0.26
    æ¯ıå¹´
    0.25
    åıĤåĬł
    0.24
    主åĬŀæĸ¹
    0.23
    èµĽäºĭ
    0.23
    åħ¥åľº
    0.23
     participation
    0.23
     participants
    0.22
    æį¢
    0.22
    ä¸Ī
    0.21
    Activations Density 0.028%

    No Known Activations