© 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. 12007
    Prev
    Next
    INDEX
    Explanations

    Prime Minister

    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
    åѤ
    -0.19
    æĺ¯ä¸ĢåIJį
    -0.19
    è´§
    -0.18
    å¾Ĺ天çĭ¬
    -0.18
    -base
    -0.18
     unst
    -0.18
    åľ¨çݩ家ä¸Ń
    -0.18
    足
    -0.17
    İ·
    -0.17
    æĪ¿ç§Ł
    -0.17
    POSITIVE LOGITS
    åħ¼
    0.27
     Tul
    0.24
    æ¸ħç®Ĺ
    0.21
    çĺ¾
    0.19
     Aviv
    0.19
    åĬ©çIJĨ
    0.19
    iators
    0.19
    EGIN
    0.19
    é©·
    0.18
    겸
    0.18
    Activations Density 0.017%

    No Known Activations