© 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. 13117
    Prev
    Next
    INDEX
    Explanations

    of others, those

    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
    ä¸Ģåıª
    -0.19
    _gc
    -0.19
    æĬµ
    -0.18
    ç¯Ļ
    -0.18
    feed
    -0.18
    ì¹ĺ
    -0.17
    樽
    -0.17
    зад
    -0.17
    atti
    -0.17
    ettes
    -0.17
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.33
    åħ¶å®ĥ
    0.33
     other
    0.32
    åĪ«çļĦ
    0.31
    åħ¶ä»ĸçļĦ
    0.31
    åħ¶ä»ĸ
    0.31
     similarly
    0.30
     equally
    0.29
     дÑĢÑĥгие
    0.27
     дÑĢÑĥгиÑħ
    0.26
    Activations Density 0.102%

    No Known Activations