© 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. 13019
    Prev
    Next
    INDEX
    Explanations

    building spaces

    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
    æĹı
    -0.20
     enlightened
    -0.20
    dale
    -0.20
    ale
    -0.19
    ear
    -0.19
    ales
    -0.19
    éĩįçİ°
    -0.18
    赶
    -0.18
    形容
    -0.18
    çĸĹç¨ĭ
    -0.18
    POSITIVE LOGITS
    åħ¼
    0.27
    æĢ»éĿ¢ç§¯
    0.25
    겸
    0.24
    éĿ¢ç§¯çº¦
    0.24
    ä¸Ģ个å°ı
    0.24
    æĿĤçī©
    0.24
    éŨåīį
    0.23
     ÑħозÑıйÑģÑĤв
    0.23
    éŨ
    0.21
    éĿ¢ç§¯
    0.20
    Activations Density 0.034%

    No Known Activations