© 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. 11768
    Prev
    Next
    INDEX
    Explanations

    surnames followed by punctuation

    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
    èĥ½åĬĽåĴĮ
    -0.23
    è´¨éĩıåĴĮ
    -0.22
    åįķçĭ¬
    -0.20
    ç»ıéªĮåĴĮ
    -0.20
    iful
    -0.19
    ä¼ģä¸ļåĴĮ
    -0.18
    ãĤĦ
    -0.18
    æĽ
    -0.18
    ä¸İåħ¶ä»ĸ
    -0.17
    _BS
    -0.17
    POSITIVE LOGITS
     eds
    0.28
    >tag
    0.20
     Partner
    0.19
     Streets
    0.18
    çļ´
    0.17
     partner
    0.17
     Tinder
    0.17
     Jr
    0.17
    ä½İä¼°
    0.17
    è¿ĻèĪ¬
    0.16
    Activations Density 0.111%

    No Known Activations