© 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. 15692
    Prev
    Next
    INDEX
    Explanations

    email headers, licenses, software names

    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
    åľ°ä¸Ĭ
    -0.18
     Alb
    -0.18
    rosse
    -0.18
    ted
    -0.18
    ainment
    -0.17
     ])
    -0.17
     }}">{{
    -0.17
     porte
    -0.16
     Vet
    -0.16
     Felix
    -0.16
    POSITIVE LOGITS
    èĢĮè¨Ģ
    0.21
    _Sh
    0.19
    èĢģ人家
    0.18
    ⣩
    0.18
    ⣫
    0.18
    è¦ģç´§
    0.18
    æīĵçĶµè¯Ŀ
    0.17
    âĹĢ
    0.17
    鸬
    0.17
    æĤł
    0.16
    Activations Density 0.466%

    No Known Activations