© 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. 15455
    Prev
    Next
    INDEX
    Explanations

    groups, database, first, act, hashes, bleeding, private, training, moderator, inheritance

    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
    ILER
    -0.18
    èĻ¬
    -0.18
    iland
    -0.18
     both
    -0.18
     Yup
    -0.17
    both
    -0.17
    bbie
    -0.17
    è¡¿
    -0.17
    éĦĤ
    -0.17
     boÅŁ
    -0.17
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.41
     nor
    0.30
    æľīä»»ä½ķ
    0.28
    æĪĸæĺ¯
    0.28
    æĪĸåħ¶ä»ĸ
    0.27
    æĪĸå¤ļ
    0.26
    æĪĸ
    0.24
     или
    0.24
    ä»»ä½ķ人
    0.23
     sondern
    0.23
    Activations Density 0.292%

    No Known Activations