© 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. 14901
    Prev
    Next
    INDEX
    Explanations

    adjectives describing media or content

    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
    sic
    -0.25
    folio
    -0.22
     sic
    -0.20
    ãģªãĤĵãģ¦
    -0.20
     promin
    -0.19
    å½¢åĬ¿
    -0.19
    家åĸ»
    -0.19
    Ign
    -0.18
    åĽłåľ°åĪ¶
    -0.18
    åįĥæĸ¹çĻ¾
    -0.18
    POSITIVE LOGITS
    è´¨
    0.20
    éĩİå¿ĥ
    0.19
    amburger
    0.19
    THON
    0.19
    åºŁè¯Ŀ
    0.18
    lectual
    0.18
    ä¸ĢåĪĩ
    0.18
    æĢ§åĴĮ
    0.17
    çݯä¿Ŀ
    0.17
     earned
    0.17
    Activations Density 0.077%

    No Known Activations