© 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. 12457
    Prev
    Next
    INDEX
    Explanations

    coins

    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
    Lite
    -0.19
    å·¦æīĭ
    -0.18
    ublish
    -0.18
    æĭ¼
    -0.18
    åıij表
    -0.18
    gne
    -0.18
    åħ¬å¼Ģ课
    -0.18
    -auth
    -0.18
    clause
    -0.17
    åºIJ
    -0.17
    POSITIVE LOGITS
     alike
    0.24
     hei
    0.22
    寡
    0.21
    iggs
    0.19
    åıĺåİĭ
    0.19
    æĪijéĥ½
    0.19
     Reid
    0.18
    hal
    0.18
     pans
    0.18
    两èĢħ
    0.18
    Activations Density 0.143%

    No Known Activations