© 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. 15265
    Prev
    Next
    INDEX
    Explanations

    announcement or key

    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
    çļĦåģļæ³ķ
    -0.20
    ye
    -0.20
    Bars
    -0.19
     dialog
    -0.18
    cols
    -0.17
    å·¥åºı
    -0.17
     prepared
    -0.17
     mechan
    -0.17
     dialogRef
    -0.17
    hiro
    -0.17
    POSITIVE LOGITS
    announce
    0.24
    宣å¸ĥ
    0.23
    oppable
    0.23
    æĴŃæĬ¥
    0.23
    åıijå¸ĥåħ¬åijĬ
    0.23
    åħ¬å¸ĥ
    0.23
    åħ¬å¸ĥçļĦ
    0.22
    å½ĵ天
    0.21
     announcement
    0.21
    å½ĵæĻļ
    0.21
    Activations Density 0.008%

    No Known Activations