© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15194
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĩĬ
    -0.21
    å®ŀæĸ½ç»ĨåĪĻ
    -0.20
    èİ·å¾ĹæĽ´å¤ļ
    -0.19
    åIJīåĪ©
    -0.18
    åħĭæľį
    -0.18
    éĩĭ
    -0.18
    å¯Ł
    -0.18
     Born
    -0.18
    çļĦ认è¯Ĩ
    -0.17
    éī´åĪ«
    -0.17
    POSITIVE LOGITS
    erra
    0.20
    ÑģÑĤавил
    0.20
     cầm
    0.19
     Trudeau
    0.19
    å¤§éĽ¨
    0.19
    sti
    0.18
    coma
    0.18
    rama
    0.18
    Ending
    0.18
    iface
    0.18
    Activations Density 0.000%

    No Known Activations