© 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. 14240
    Prev
    Next
    INDEX
    Explanations

    phrases like "it was" or "not fair"

    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
    ipsis
    -0.21
    åĿĩçĶ±
    -0.20
    lds
    -0.20
     EACH
    -0.19
    ï¿
    -0.19
    _FLOW
    -0.19
    æ¯ıä¸Ģ个
    -0.19
    .cfg
    -0.19
    å®ĮæĪIJåIJİ
    -0.18
    表éĿ¢ä¸Ĭ
    -0.18
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.32
    ä½łæĢİä¹Ī
    0.24
    XXX
    0.24
    è¿Ļä¹Īå¤ļ
    0.23
    ä½łçİ°åľ¨
    0.23
    XX
    0.22
    æľ¬æľĪ
    0.22
    è¿Ļ次
    0.20
    è¿ĻæĶ¯
    0.19
     X
    0.19
    Activations Density 0.075%

    No Known Activations