© 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. 14603
    Prev
    Next
    INDEX
    Explanations

    violation of rules or laws

    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
    ä¸Ģ对ä¸Ģ
    -0.23
    çľī
    -0.21
    人èĦī
    -0.20
    Slash
    -0.20
    åIJĦå¼Ĥ
    -0.20
    otty
    -0.20
     пÑĢид
    -0.20
    Warm
    -0.20
    ä¸İä¼Ĺä¸įåIJĮ
    -0.20
    ä¸įåIJĮäºİ
    -0.19
    POSITIVE LOGITS
    tant
    0.20
    æ³ķè§Ħ
    0.20
    yar
    0.20
    大éĿ¢ç§¯
    0.20
    å®Įæķ´æĢ§
    0.19
    åºĶæľīçļĦ
    0.19
     attempts
    0.19
    åºķ线
    0.19
    è§ĦèĮĥ
    0.19
    ä¸į说
    0.19
    Activations Density 0.047%

    No Known Activations