© 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. 14757
    Prev
    Next
    INDEX
    Explanations

    named player of the year

    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
    bolt
    -0.22
    åĩºè·¯
    -0.19
    ahir
    -0.19
    ót
    -0.19
    åıł
    -0.18
    åĩłåĪĨ
    -0.18
     disin
    -0.18
    halt
    -0.18
    ä¼į
    -0.18
     reprodu
    -0.18
    POSITIVE LOGITS
    年度
    0.28
    å½ĵä¹ĭæĹłæĦ§
    0.26
    åij½åIJį
    0.24
    è¯Ħ为
    0.24
    è¯ĦéĢī
    0.24
    è¿Ļä¸Ģå¹´
    0.23
    ä»ħ次äºİ
    0.23
    表彰
    0.23
    æ¯ı个æľĪ
    0.22
    äºĭ迹
    0.21
    Activations Density 0.022%

    No Known Activations