© 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. 14440
    Prev
    Next
    INDEX
    Explanations

    historical periods and empires

    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
    ç¿ħèĨĢ
    -0.21
    PTR
    -0.20
    .attach
    -0.19
    _operator
    -0.19
    大å§IJ
    -0.18
     isr
    -0.18
    å²Ľä¸Ĭ
    -0.18
    aston
    -0.17
    elen
    -0.17
     UIResponder
    -0.17
    POSITIVE LOGITS
    æĹ¶æľŁçļĦ
    0.39
    -era
    0.38
    æĹ¶ä»£çļĦ
    0.37
     era
    0.35
    æĹ¶æľŁ
    0.35
    æĹ¶ä»£
    0.34
    åİĨåı²
    0.33
    æĻĤ代
    0.33
     historical
    0.32
    çļĦåİĨåı²
    0.32
    Activations Density 0.127%

    No Known Activations