© 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. 14823
    Prev
    Next
    INDEX
    Explanations

    game entities and scenarios

    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
    .callback
    -0.20
    å¬ĸ
    -0.20
    ymoon
    -0.19
     songwriter
    -0.19
    èĸ®
    -0.19
    oplast
    -0.18
    èĥŃ
    -0.18
    æ±īåŃIJ
    -0.18
     обÑıз
    -0.18
    è²ĺ
    -0.18
    POSITIVE LOGITS
     behavior
    0.29
    è¡Į为
    0.26
    äºĴåĬ¨
    0.25
    èĩªåĬ¨
    0.25
     behaviour
    0.22
    èĩªåĭķ
    0.22
    æĢ§æł¼
    0.22
    åĬ¨æĢģ
    0.22
    å·¡éĢ»
    0.21
    人çī©
    0.21
    Activations Density 0.037%

    No Known Activations