© 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. 12581
    Prev
    Next
    INDEX
    Explanations

    specify, clarify, or explicitly state

    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
     Corm
    -0.20
    å¹´ä¸ĬåįĬå¹´
    -0.19
    å½ĵæĹ¥
    -0.19
    rap
    -0.19
    路桥
    -0.18
     prior
    -0.18
     Bord
    -0.18
    åIJ¸åıĸ
    -0.18
    Orm
    -0.18
    æ²ħ
    -0.17
    POSITIVE LOGITS
     explicitly
    0.31
    æĺİç¡®è§Ħå®ļ
    0.31
    æĺİç¡®
    0.31
     expressly
    0.27
    åħ·ä½ĵ
    0.26
    ç»ĨåĪĻ
    0.26
    åħ·ä½ĵçļĦ
    0.25
    ç»ĨåĮĸ
    0.23
     explicit
    0.23
    详ç»ĨçļĦ
    0.22
    Activations Density 0.049%

    No Known Activations