© 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. 16160
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĽ´éĩįè¦ģ
    -0.20
    Cro
    -0.20
    cro
    -0.20
    æĥ
    -0.19
    ä¸Ģç¬Ķ
    -0.19
    éĻ¡
    -0.19
    çģ«çĥ§
    -0.19
    常è¯Ĩ
    -0.17
    avern
    -0.17
     tháºŃm
    -0.17
    POSITIVE LOGITS
    祢
    0.19
    äºĪ以
    0.19
    éħįæĸĻ
    0.18
     hÆ°á»Łng
    0.18
    ä¸ĭçļĦ
    0.18
    æĦĶ
    0.18
    æĬĬ
    0.17
    гал
    0.17
    isman
    0.17
    emean
    0.17
    Activations Density 0.000%

    No Known Activations