© 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. 11214
    Prev
    Next
    INDEX
    Explanations

    conversational interjections and affirmations

    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
    é»ijçĻ½
    -0.21
    被称为
    -0.20
    å§ĭäºİ
    -0.20
    обоÑĢ
    -0.20
    é¬ĵ
    -0.20
    ä¸ĩ象
    -0.19
    elts
    -0.19
    CEF
    -0.19
    æī¯
    -0.18
    è¾Ľè¾£
    -0.18
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.20
    entifier
    0.19
    s
    0.19
    人家
    0.19
    ches
    0.18
    å°±çŁ¥éģĵ
    0.18
    âģ
    0.17
    æľīæķĪæľŁ
    0.17
    ane
    0.17
     smoke
    0.17
    Activations Density 0.020%

    No Known Activations