© 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. 15638
    Prev
    Next
    INDEX
    Explanations

    video recording devices

    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
    çĺ´
    -0.22
    æľ¨åľ°æĿ¿
    -0.21
    KER
    -0.21
    åıĭæĥħéĵ¾æİ¥
    -0.21
     evac
    -0.19
    æ°Ľ
    -0.19
    yat
    -0.18
    ç½ijç«Ļ建设
    -0.18
    THR
    -0.18
    èĴĻ
    -0.18
    POSITIVE LOGITS
    ideo
    0.22
    秣
    0.21
    çķĻä½ı
    0.21
    ä¸ĢæĹı
    0.21
    èģĥ
    0.20
    çŃĸçķ¥
    0.20
    icut
    0.18
    Fu
    0.18
    èĥ½åĬĽ
    0.18
    èĩªåĬ¨
    0.18
    Activations Density 0.005%

    No Known Activations