© 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. 11367
    Prev
    Next
    INDEX
    Explanations

    D&D and RPGs

    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
    æŁĶæĢ§
    -0.19
    å¯Ł
    -0.18
    /details
    -0.17
    EMBER
    -0.17
    ¾ç¤º
    -0.17
    uell
    -0.17
    Extern
    -0.17
     Yıl
    -0.17
    aiser
    -0.17
     ÑĥпÑĢавлениÑı
    -0.17
    POSITIVE LOGITS
     Epic
    0.21
     Dungeons
    0.21
    æ¡Įä¸Ĭ
    0.20
    æĹ¶æľŁçļĦ
    0.20
    -Core
    0.20
    ç°ª
    0.20
    è¿·
    0.19
    åĽ½åº¦
    0.19
     Abrams
    0.18
    çļĦéŃħåĬĽ
    0.18
    Activations Density 0.010%

    No Known Activations