© 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. 15801
    Prev
    Next
    INDEX
    Explanations

    even if

    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¦Ĥæŀľè¯´
    -0.22
    èĢĮ导èĩ´
    -0.19
    ä»Ģä¹Īæł·çļĦ
    -0.18
    æ¯Ķå¦Ĥ说
    -0.18
    就好äºĨ
    -0.18
    å°±å¿ħé¡»
    -0.18
    æĪIJçĨŁçļĦ
    -0.18
    ä¹ĭç±»çļĦ
    -0.18
    ä¹ħäºĨ
    -0.18
    æĢ»ä¹ĭ
    -0.17
    POSITIVE LOGITS
    å®ĥ
    0.31
    å®ĥæĺ¯
    0.29
    åħ¶
    0.23
    å®ĥçļĦ
    0.22
    åħ¶æīĢ
    0.21
     it
    0.21
    å®ĥ们
    0.21
     اÙĦØ£Ùħر
    0.19
     they
    0.19
    åľ°å¤Ħ
    0.18
    Activations Density 0.022%

    No Known Activations