© 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. 15758
    Prev
    Next
    INDEX
    Explanations

    challenges and problems

    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
    åĵ¨
    -0.20
    åĩĨåĪĻ
    -0.20
    tin
    -0.20
    è¿Ļç§įæĸ¹å¼ı
    -0.19
    .opensource
    -0.19
    æĮĩ导ä¸ĭ
    -0.19
    æľīæĿ¡ä»¶
    -0.19
    æ©IJ
    -0.19
    绿èī²éĢļéģĵ
    -0.18
    马åĬĽ
    -0.18
    POSITIVE LOGITS
    çļĦéĹ®é¢ĺ
    0.42
    è¿ĻäºĽéĹ®é¢ĺ
    0.40
     issues
    0.37
    ä¸Ģ个éĹ®é¢ĺ
    0.37
    åĽ°æī°
    0.35
    éĹ®é¢ĺ
    0.35
     problems
    0.34
     пÑĢоблемÑĭ
    0.34
    åķıé¡Į
    0.33
    éĩįéĩį
    0.33
    Activations Density 0.264%

    No Known Activations