© 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. 16812
    Prev
    Next
    INDEX
    Explanations

    Javascript to register

    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
    ær
    -0.21
    ä½ij
    -0.19
    åºı
    -0.19
    bis
    -0.19
    atsu
    -0.19
    ä¿İ
    -0.18
     Nero
    -0.18
    yan
    -0.18
    ä¸ĬéŨ
    -0.18
    纳åħ¥
    -0.17
    POSITIVE LOGITS
    æīįåı¯ä»¥
    0.20
    asd
    0.20
    æīįèĥ½å¤Ł
    0.19
    æ·±åĮĸæĶ¹éĿ©
    0.19
    è¿Ļ个æŶåĢĻ
    0.19
    ä¸ĭè¡Į
    0.19
    æīįèĥ½
    0.18
    QUEUE
    0.17
     delegate
    0.17
    rack
    0.17
    Activations Density 0.005%

    No Known Activations