© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15404
    Prev
    Next
    INDEX
    Explanations

    medical emergencies and 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
    ä¿ı
    -0.21
    å°¾
    -0.21
    骨
    -0.20
    å¦Ļ
    -0.20
    佬
    -0.20
    icide
    -0.20
    ä¿®å¤į
    -0.20
    尾巴
    -0.19
    çģ¾åĮº
    -0.19
    åĸ»
    -0.19
    POSITIVE LOGITS
    è¨Ģè¡Į
    0.21
    表çİ°
    0.21
    çļĦ表çİ°
    0.21
    åıįåºĶ
    0.21
    _rewrite
    0.20
    eon
    0.20
    å¹»
    0.20
    åıijä½ľ
    0.20
    éĻŁ
    0.19
    çªģåıij
    0.19
    Activations Density 0.045%

    No Known Activations