© 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. 16323
    Prev
    Next
    INDEX
    Explanations

    with a expert

    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
    è¿Ļæĺ¯æĪij
    -0.20
    山路
    -0.19
    å°ıå§ijå¨ĺ
    -0.19
    åĬĽ
    -0.19
    ä¼Ļä¼´åħ³ç³»
    -0.18
    ç»ĻåĪ«äºº
    -0.18
    åĽĽå¤Ħ
    -0.18
    ä¸įè´Ł
    -0.18
    åħ¬çĽĬæ´»åĬ¨
    -0.18
    ä»Ĥ
    -0.18
    POSITIVE LOGITS
    ä¸ĵ家
    0.30
     expert
    0.27
     experts
    0.24
     specially
    0.24
    ä¸ĵ人
    0.23
    ä¸ĵ家ç»Ħ
    0.22
    å½ĵåľ°
    0.21
    åIJĪæł¼
    0.21
    åIJįå¸Ī
    0.21
    æĩĤ
    0.20
    Activations Density 0.030%

    No Known Activations