© 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. 16751
    Prev
    Next
    INDEX
    Explanations

    functional followed by nouns

    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
    tures
    -0.18
    éľĨ
    -0.18
    ened
    -0.18
    èľ¿
    -0.17
    ä¸Ģå°ģ
    -0.16
    dump
    -0.16
    è¡·
    -0.16
    stakes
    -0.16
    åĪ¶åº¦æĶ¹éĿ©
    -0.16
    å¾Ĺèµ·
    -0.15
    POSITIVE LOGITS
    æĢ§å¼º
    0.26
    æĢ§åĴĮ
    0.19
    æĢ§çļĦ
    0.19
    -looking
    0.18
    uration
    0.16
    ноÑģÑĤ
    0.16
    ism
    0.16
     må
    0.15
    -tools
    0.15
    -minded
    0.15
    Activations Density 0.041%

    No Known Activations