© 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. 12767
    Prev
    Next
    INDEX
    Explanations

    future trends continue

    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
    дей
    -0.21
     конкÑĢеÑĤ
    -0.19
    æ±Ľ
    -0.19
    å°¤åħ¶
    -0.19
    łģ
    -0.19
    çģµæ°Ķ
    -0.18
    æ¸IJæ¸IJ
    -0.18
    PTS
    -0.18
    åĪ
    -0.18
    éľĸ
    -0.18
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.39
    就好äºĨ
    0.34
    çļĦ話
    0.32
    å°±ä¼ļ
    0.24
    è¿Ļæł·çļĦè¯Ŀ
    0.24
    íķľëĭ¤ë©´
    0.23
    ï¼ĮåĪĻ
    0.23
    ëĿ¼ë©´
    0.22
     would
    0.21
    è¡Į使
    0.21
    Activations Density 0.089%

    No Known Activations