© 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. 11825
    Prev
    Next
    INDEX
    Explanations

    talks and lectures

    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
     пÑĥнкÑĤ
    -0.20
    strup
    -0.20
    æģ«
    -0.19
    çŃĴ
    -0.18
    jun
    -0.18
    ional
    -0.18
     apart
    -0.18
    åºķæ°Ķ
    -0.17
     Neh
    -0.17
    æ¡Ķ
    -0.17
    POSITIVE LOGITS
    讲座
    0.23
    æļ¨
    0.22
    æ·¡æ·¡çļĦ
    0.20
    两个å°ıæŶ
    0.20
    oden
    0.20
     RU
    0.20
    å±ĬæŶ
    0.19
    åħ¼
    0.19
    èĥ½æ»¡è¶³
    0.19
     lecture
    0.19
    Activations Density 0.027%

    No Known Activations