© 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. 12676
    Prev
    Next
    INDEX
    Explanations

    glass and crystal objects

    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
    å¤ĩæĪĺ
    -0.21
    æĪ¢
    -0.21
    çıłä¸īè§Ĵ
    -0.20
    æĴij
    -0.19
    azy
    -0.19
    éĻĤ
    -0.19
     painted
    -0.19
     Paint
    -0.18
    åĤĻ
    -0.18
    paint
    -0.18
    POSITIVE LOGITS
    egin
    0.21
    yle
    0.21
    æ°´æĻ¶
    0.20
    YLE
    0.20
    çݯç»ķ
    0.19
    .vert
    0.19
    çŃ¾çº¦ä»ªå¼ı
    0.18
    gt
    0.18
    å¢ŀæ·»
    0.18
    .effect
    0.17
    Activations Density 0.004%

    No Known Activations