© 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. 14992
    Prev
    Next
    INDEX
    Explanations

    improvement and progress

    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
    åı¯æĢľ
    -0.22
    itage
    -0.22
    ëĿ¼ëıĦ
    -0.20
    åħ»çĶŁ
    -0.19
    èĢĻ
    -0.19
    istics
    -0.19
    itorio
    -0.19
    带走
    -0.18
    scp
    -0.18
    ä¹±
    -0.18
    POSITIVE LOGITS
    è¿ĽæŃ¥
    0.25
    æĪIJçĨŁ
    0.24
    åѦä¼ļäºĨ
    0.23
    å¾ĹçĽĬäºİ
    0.22
    åıĹçĽĬ
    0.21
     improve
    0.21
    æıIJé«ĺ
    0.21
    æĪIJéķ¿ä¸º
    0.20
     grow
    0.20
     thanks
    0.20
    Activations Density 0.029%

    No Known Activations