© 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. 14542
    Prev
    Next
    INDEX
    Explanations

    total, overall, or composite counts

    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
    çıŃ
    -0.20
    è¿Ħ
    -0.19
    ilian
    -0.19
    çĶļèĩ³
    -0.18
    ä¸įåIJĮäºİ
    -0.18
    _SS
    -0.18
    lessly
    -0.18
    ä¸įåıªæĺ¯
    -0.18
    çŃ¾çº¦
    -0.18
     profil
    -0.18
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.38
     overall
    0.32
    çļĦæķ´ä½ĵ
    0.29
    Overall
    0.29
     Overall
    0.28
    æĢ»çļĦ
    0.27
    æĢ»ä½ĵ
    0.26
    overall
    0.25
    å¤įåIJĪ
    0.24
     composite
    0.22
    Activations Density 0.242%

    No Known Activations