© 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. 15020
    Prev
    Next
    INDEX
    Explanations

    essay or research paper topic

    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
    è¿IJç»´
    -0.23
    Equivalent
    -0.23
    Indexed
    -0.21
    é£İæݧ
    -0.21
    idx
    -0.21
    åħ¨æµģç¨ĭ
    -0.21
    ฯ
    -0.21
    ->{
    -0.20
    åIJİç»Ń
    -0.20
    ãģ£ãģ¡ãĤĥ
    -0.20
    POSITIVE LOGITS
    åľ¨çĶŁæ´»ä¸Ń
    0.34
    æĪij认为
    0.28
    让人们
    0.25
     Essay
    0.23
     essay
    0.23
    æĩĤå¾Ĺ
    0.23
    .zoom
    0.22
    åĿļæĮģä¸įæĩĪ
    0.21
    家乡
    0.21
    _IMP
    0.21
    Activations Density 0.133%

    No Known Activations