© 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. 15741
    Prev
    Next
    INDEX
    Explanations

    barcode scanner

    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
    hev
    -0.21
    梳
    -0.20
     Vad
    -0.20
    æĢģ
    -0.19
    éĹ©
    -0.19
    蹬
    -0.19
    awi
    -0.19
    onis
    -0.18
    纫
    -0.18
    ä¿¡ç®±
    -0.18
    POSITIVE LOGITS
    è¯ĨåĪ«
    0.29
    äºĮç»´çłģ
    0.24
    åľ¨çĶŁæ´»ä¸Ń
    0.21
     бÑĥм
    0.20
    导åħ¥
    0.20
    æī«æıı
    0.20
    æī«çłģ
    0.20
     инÑĤеÑĢеÑģ
    0.20
     scanner
    0.19
    scanner
    0.19
    Activations Density 0.026%

    No Known Activations