© 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. 11604
    Prev
    Next
    INDEX
    Explanations

    members and judges

    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°ıåŃIJ
    -0.19
    çĭ·
    -0.19
    å°Ħæīĭ
    -0.19
    æĮĽ
    -0.19
    å³Ħ
    -0.18
    çīł
    -0.18
    åŃĺåľ¨äºİ
    -0.18
    çݰ象
    -0.18
    åĽĽäºĶ
    -0.18
     Randall
    -0.18
    POSITIVE LOGITS
    们
    0.26
    纷纷表示
    0.23
    们çļĦ
    0.23
    åIJĦèĩª
    0.22
    åIJĦ
    0.21
     пÑĢиÑıÑĤн
    0.21
    åIJĦèĩªçļĦ
    0.21
    ä¹ĭéĹ´çļĦ
    0.21
     themselves
    0.21
    ç»ĦæĪIJçļĦ
    0.20
    Activations Density 0.016%

    No Known Activations