© 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. 15704
    Prev
    Next
    INDEX
    Explanations

    numbers and degrees Celsius

    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
    -ed
    -0.21
    踩
    -0.20
     complement
    -0.20
    ç´¢åıĸ
    -0.20
    moz
    -0.19
    asis
    -0.19
    ä¸įæŃ¢
    -0.19
    ä¸įçŁ¥
    -0.18
    BT
    -0.18
     complementary
    -0.18
    POSITIVE LOGITS
    çĶŁæ´»ä¹łæĥ¯
    0.26
    ssp
    0.21
    åIJĪãģĦ
    0.20
     Lawson
    0.19
    .innerHeight
    0.19
    åij¼åĴĮ
    0.18
     اÙĦعÙĦÙĬا
    0.18
    .nextToken
    0.18
    åıįåºĶ
    0.18
    NAL
    0.18
    Activations Density 0.104%

    No Known Activations