© 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. 12781
    Prev
    Next
    INDEX
    Explanations

    everything from

    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
    ç®ĢåįķçļĦ
    -0.24
    å°±
    -0.20
    ä¸Ģè¶Ł
    -0.19
    å°±ç®Ĺæĺ¯
    -0.18
    æ¯ı个人éĥ½
    -0.18
     tent
    -0.18
    çľĭçĶµè§Ĩ
    -0.18
    ä¸ĢäºĽ
    -0.17
    tent
    -0.17
    lsi
    -0.17
    POSITIVE LOGITS
     обо
    0.23
    äºĭå®ľ
    0.22
    åıĺå¹»
    0.21
     demás
    0.21
    ä¹ĭäºĭ
    0.20
    çļĦä¸ĢåĪĩ
    0.19
    ä¹ĭç¾İ
    0.19
    çļĨ
    0.19
     ÑģвÑıзан
    0.19
    秩
    0.19
    Activations Density 0.012%

    No Known Activations