© 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. 13428
    Prev
    Next
    INDEX
    Explanations

    life sentence

    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
    å¥ĩ
    -0.21
    å·½
    -0.21
     simult
    -0.19
    æݢ究
    -0.19
    æľªç»ıæİĪæĿĥ
    -0.19
    æĺŁçIJĥ
    -0.19
    çĤ¹å¤ļ
    -0.18
    ä¹Łæ¯Ķè¾ĥ
    -0.18
    躺çĿĢ
    -0.18
    çĩİ
    -0.18
    POSITIVE LOGITS
    otechnology
    0.19
     closet
    0.19
    ity
    0.18
    mpl
    0.18
    èĶ½
    0.17
    æī£
    0.17
    ÙĪÙĬ
    0.17
    ধ
    0.17
     Moms
    0.17
    arat
    0.17
    Activations Density 0.003%

    No Known Activations