© 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. 14943
    Prev
    Next
    INDEX
    Explanations

    you're doing it

    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
    amm
    -0.22
    Downloads
    -0.22
     Dorm
    -0.20
    æ¹
    -0.20
    åĬ¾
    -0.19
    å°±è¿Ļæł·
    -0.19
    udent
    -0.19
    社ä¼ļåIJĦçķĮ
    -0.18
    ãģĻãĤĭãģŁãĤģãģ«
    -0.18
     boycott
    -0.18
    POSITIVE LOGITS
     either
    0.23
     likely
    0.20
     probably
    0.20
    buckets
    0.20
    å¾Īåı¯èĥ½
    0.19
    [".
    0.19
    rowned
    0.19
    æĺŃ
    0.19
     Likely
    0.18
    boards
    0.18
    Activations Density 0.054%

    No Known Activations