© 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. 15384
    Prev
    Next
    INDEX
    Explanations

    food descriptions

    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
    inkel
    -0.21
    è£Ĩ
    -0.21
    виÑĤ
    -0.19
    è½®åĽŀ
    -0.19
    asher
    -0.19
    贯穿
    -0.19
    åĪ©äºİ
    -0.19
    åľ¨æľªæĿ¥
    -0.18
    åıĹéĻIJ
    -0.18
    ippet
    -0.18
    POSITIVE LOGITS
    æľįåĬ¡è´¨éĩı
    0.25
    è´¨éĩıåĴĮ
    0.23
    è¿ĻéĩĮçļĦ
    0.23
    åĢ¼å¾Ĺä¸Ģ
    0.20
     quality
    0.20
    (review
    0.19
    scoped
    0.19
    åĩºèī²
    0.19
    MenuItem
    0.19
    onest
    0.19
    Activations Density 0.017%

    No Known Activations