© 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. 16891
    Prev
    Next
    INDEX
    Explanations

    rather or instead

    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
    ä½Ĩ她
    -0.22
    çĶļèĩ³è¿ĺ
    -0.21
    é¢ĩ为
    -0.21
    éĿŀ常åĸľæ¬¢
    -0.20
    ä¸įå°ı
    -0.20
    å¼Ģå±Ģ
    -0.20
    ç¾İ好çĶŁæ´»
    -0.19
    äºĨä¸įå°ij
    -0.19
    ä¸įä»ħæĺ¯
    -0.19
    æŀĦæĢĿ
    -0.19
    POSITIVE LOGITS
    æīįæĺ¯
    0.39
    è¿Ļæīįæĺ¯
    0.38
    èĢĮä¸įæĺ¯
    0.36
     rather
    0.31
    æīįæĺ¯çľŁæŃ£
    0.28
     chứ
    0.28
    èĢĮéĿŀ
    0.27
    rather
    0.27
     instead
    0.23
     Rather
    0.23
    Activations Density 0.090%

    No Known Activations