© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10451
    Prev
    Next
    INDEX
    Explanations

    animals and mammals

    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
    Negative Logits
    åİŁåĽłæĺ¯
    -0.20
    说çļĦæĺ¯
    -0.19
    ä¸ĢåĢĭ人
    -0.18
    -peer
    -0.18
    xDD
    -0.18
    æĬķå½±
    -0.18
    éĺı
    -0.18
    leases
    -0.18
    åĽłä¸ºæĪij们
    -0.18
    Projection
    -0.18
    POSITIVE LOGITS
    è¶Ĭå¤ļ
    0.22
    éĥ½åºĶ该
    0.22
    åºĸ
    0.21
    aines
    0.20
    æģ
    0.20
     Colbert
    0.19
    é»ĺå¥ij
    0.18
     sapi
    0.18
     pants
    0.18
    ntl
    0.18
    Activations Density 0.235%

    No Known Activations