© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12631
    Prev
    Next
    INDEX
    Explanations

    able to perform well

    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
    èĢ½è¯¯
    -0.21
    åĬŁèĥ½æĢ§
    -0.20
    太ä¹ħ
    -0.20
    æĿŁç¼ļ
    -0.20
    两åij¨
    -0.19
    èĨı
    -0.19
     Brom
    -0.18
    åı©
    -0.18
    ç»ĵæĿŁäºĨ
    -0.18
    .va
    -0.18
    POSITIVE LOGITS
    æīįèĥ½
    0.35
    æīįè¡Į
    0.35
    èĢIJå¿ĥ
    0.30
    æīįåı¯ä»¥
    0.29
    è¦ģæľī
    0.27
    ä¸įä»ħè¦ģ
    0.26
    æīįèĥ½å¤Ł
    0.25
    æĬĢå·§
    0.24
     patience
    0.24
    çģµæ´»
    0.23
    Activations Density 0.131%

    No Known Activations