© 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. 15529
    Prev
    Next
    INDEX
    Explanations

    supposed party

    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
    çĽ¸å¯¹è¾ĥ
    -0.22
    åīĤéĩı
    -0.22
    дов
    -0.21
    éĩİå¿ĥ
    -0.20
    åŃķæľŁ
    -0.20
    侧éĿ¢
    -0.19
    è¿Ľé¡¹
    -0.19
    积æŀģåıĤä¸İ
    -0.19
    æ½ľåľ¨
    -0.19
    à¹ģ
    -0.19
    POSITIVE LOGITS
     Zap
    0.21
    ÃŃv
    0.21
    	HX
    0.20
    ãĢģ“
    0.20
     “
    0.20
    .learn
    0.19
     desk
    0.19
    osed
    0.19
     training
    0.19
    Îŀ
    0.19
    Activations Density 0.043%

    No Known Activations