© 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. 14269
    Prev
    Next
    INDEX
    Explanations

    Tibet plateau

    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
    天ä¸ĭ
    -0.21
    uchi
    -0.20
    äºĭåħĪ
    -0.20
    æ·±èĢķ
    -0.20
    家çĶµ
    -0.19
     Cincinnati
    -0.19
    诣
    -0.18
    åĬ¾
    -0.18
    éĤĹ
    -0.18
    Ùħرا
    -0.18
    POSITIVE LOGITS
    å°ijæķ°æ°ijæĹı
    0.27
    æ°ijæĹı
    0.26
    ç³Į
    0.24
    æ°ijæĹıæĸĩåĮĸ
    0.22
    èĩªæ²»
    0.22
    è¥¿åŁŁ
    0.22
    éĽªå±±
    0.21
     minority
    0.21
    å°ķ
    0.20
    社ä¼ļåIJĦçķĮ
    0.20
    Activations Density 0.013%

    No Known Activations