© 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. 11616
    Prev
    Next
    INDEX
    Explanations

    GPU clock rate and memory

    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
     sud
    -0.21
    íĭĢ
    -0.20
    .await
    -0.20
    人çĶŁ
    -0.19
     chained
    -0.19
    .enumer
    -0.18
     chim
    -0.18
     behaviors
    -0.18
     anywhere
    -0.18
     timid
    -0.18
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.25
    åıįèħIJ
    0.23
     Radeon
    0.22
    æīĩ
    0.21
    æĶ¯æĮģåĬĽåº¦
    0.20
    gart
    0.19
    è§Ħæł¼
    0.19
    çĻ»åľº
    0.19
    è·Łéļı
    0.19
    ãĤ®ãĥ£
    0.19
    Activations Density 0.006%

    No Known Activations