© 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. 15068
    Prev
    Next
    INDEX
    Explanations

    names after "and"

    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
    ä¼łçľŁ
    -0.22
    à¹Ĥรà¸ĩà¸ŀยา
    -0.20
    à¸Ħà¸ĵะà¸ģรรม
    -0.19
     ful
    -0.19
    ä¹ŁåĽłæѤ
    -0.19
    åįķ身
    -0.18
    à¹Ģà¸Ĺศà¸ģา
    -0.18
    åįĥéĩĮ
    -0.18
    伫
    -0.18
    æĬĬå®ĥ
    -0.18
    POSITIVE LOGITS
    ä¸įæĦ¿
    0.20
    -sw
    0.19
    è¿İ
    0.19
    ETS
    0.19
    å¦Ĥæľīä¾µæĿĥ
    0.19
    æĸ¹å¼ıè¿Ľè¡Į
    0.19
    third
    0.18
    getParameter
    0.18
    åģĩè£ħ
    0.18
    Thai
    0.18
    Activations Density 0.018%

    No Known Activations