© 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. 16348
    Prev
    Next
    INDEX
    Explanations

    additional features and services

    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
    æĹłå½¢
    -0.20
    主
    -0.20
    izzy
    -0.20
    ä¸ĢåĪĨ
    -0.19
     right
    -0.18
    hab
    -0.18
    èĢĮä¸Ķ
    -0.18
    çļĦç¡®æĺ¯
    -0.17
    rys
    -0.17
    èĢĮ
    -0.17
    POSITIVE LOGITS
    诸å¦Ĥ
    0.31
    åħ¶ä»ĸçļĦ
    0.30
    次è¦ģ
    0.30
    æĿĤ
    0.28
    åħ¶ä»ĸ
    0.28
    çī¹æ®ĬæĥħåĨµ
    0.27
    åħ¶ä»ĸåĽ½å®¶
    0.26
     miscellaneous
    0.25
    additional
    0.25
    éĻĦåĬł
    0.25
    Activations Density 0.114%

    No Known Activations