© 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. 12840
    Prev
    Next
    INDEX
    Explanations

    headache and migraine conditions

    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
    arked
    -0.21
    红åĪ©
    -0.19
    alion
    -0.19
    éŀĭåŃIJ
    -0.19
    éºĴ
    -0.19
    èĪ¹ä¸Ĭ
    -0.18
    liquid
    -0.18
    æ´»åĬĽ
    -0.18
    åĿļå®ļ
    -0.18
    彤
    -0.18
    POSITIVE LOGITS
    åıijä½ľ
    0.28
    头çĹĽ
    0.24
     headache
    0.23
     headaches
    0.21
    ients
    0.21
     pain
    0.20
    å®ľ
    0.20
    éĺĻ
    0.19
    .Headers
    0.19
    çĸ¼çĹĽ
    0.19
    Activations Density 0.016%

    No Known Activations