© 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. 16320
    Prev
    Next
    INDEX
    Explanations

    still / continues

    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
    é¢ĦåħĪ
    -0.21
    äºĭåħĪ
    -0.20
    ç§įç§į
    -0.19
    ä¼ĹæīĢ
    -0.19
    鸡汤
    -0.19
    ä¸Ģè§Ī
    -0.19
    ialog
    -0.18
    fault
    -0.18
    ç²ij
    -0.18
    ÑĮÑİ
    -0.17
    POSITIVE LOGITS
    ä»įåľ¨
    0.28
    ä»įæľª
    0.27
    èĩ³ä»Ĭ
    0.26
    ä»įçĦ¶
    0.26
    ä¾ĿçĦ¶
    0.25
     still
    0.24
    ä»įçĦ¶æĺ¯
    0.23
    为æŃ¢
    0.23
    ä»į
    0.23
     till
    0.23
    Activations Density 0.059%

    No Known Activations