© 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. 15584
    Prev
    Next
    INDEX
    Explanations

    natives are, area., Senior Private, Coach McBride

    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
    pii
    -0.24
    åİĤæĪ¿
    -0.20
    é£ŀè¡Į
    -0.19
    usercontent
    -0.19
    æĤ¬æµ®
    -0.19
    .precision
    -0.18
    cargo
    -0.18
    è¿Ĥ
    -0.18
    严åİī
    -0.18
    æ¶Ĥ
    -0.18
    POSITIVE LOGITS
    èĬĤæ°´
    0.29
     landscaping
    0.28
    æݨ广åºĶçĶ¨
    0.25
    åĽŃæŀĹ
    0.23
    æݨèįIJ
    0.23
    æ¶Ŀ
    0.23
     Permanent
    0.23
    åĽŃ
    0.23
    guide
    0.23
    æĻ¯è§Ĥ
    0.22
    Activations Density 0.017%

    No Known Activations