© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12593
    Prev
    Next
    INDEX
    Explanations

    TV and television related terms

    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
    èĸ®
    -0.24
    å¥Ħ
    -0.21
    çĭ¼
    -0.20
    è£Ļ
    -0.20
    æ¢ħèĬ±
    -0.19
    icago
    -0.19
    -China
    -0.19
    æ¼ī
    -0.19
    èĢĮæĺ¯
    -0.18
    ä¸Ģ头
    -0.18
    POSITIVE LOGITS
    oons
    0.22
     NIC
    0.19
    xo
    0.19
     SER
    0.18
    å¤ĸéĿ¢
    0.18
    å½±éŁ³
    0.18
    ä¸Ģå¥Ĺ
    0.17
    QueryString
    0.17
    Scaler
    0.17
    復
    0.17
    Activations Density 0.004%

    No Known Activations