© 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. 14236
    Prev
    Next
    INDEX
    Explanations

    deluded others

    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
     @{
    -0.24
    æĪIJ为ä¸ŃåĽ½
    -0.22
    UNS
    -0.21
    åĩºæĿ¥äºĨ
    -0.20
     privé
    -0.19
    HF
    -0.19
    æĬķèµĦ人
    -0.18
     bos
    -0.18
    审
    -0.18
    hone
    -0.18
    POSITIVE LOGITS
    åıįæŃ£
    0.27
    æł¹æľ¬ä¸į
    0.24
    ä¸įè¿ĩæĺ¯
    0.23
    ä¼ģ
    0.22
     Ùħجرد
    0.21
    ä»ħä»ħæĺ¯
    0.20
    åıªä¸įè¿ĩæĺ¯
    0.20
     mere
    0.20
    ä¼¼ä¹İ
    0.20
    ä¸ĩäºĭ
    0.20
    Activations Density 0.187%

    No Known Activations