© 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. 14513
    Prev
    Next
    INDEX
    Explanations

    making a difference

    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
    боÑĤ
    -0.20
    ä¹ĭä½Ļ
    -0.19
     reluct
    -0.19
     Horizon
    -0.18
     corrid
    -0.18
    ä¸Ģåı¥
    -0.18
    æıĨ
    -0.18
    LM
    -0.18
    åĭĥ
    -0.18
    èĴ¿
    -0.18
    POSITIVE LOGITS
    åĽłä¸ºä»ĸ们
    0.30
    è¿Ļä¹Īåģļ
    0.29
     because
    0.29
    åĽłä¸ºæĪij们
    0.29
    åĽłä¸ºå®ĥ
    0.28
    åĽłä¸ºå¥¹
    0.28
     поÑĤомÑĥ
    0.27
     çünkü
    0.26
     porque
    0.25
    åĽłä¸ºä½ł
    0.25
    Activations Density 0.137%

    No Known Activations