© 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. 15233
    Prev
    Next
    INDEX
    Explanations

    worn by, served in, free to

    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
    åĬĽè¿ĺæĺ¯
    -0.20
    lor
    -0.19
     Jarvis
    -0.18
     Bá
    -0.18
    ä¼ĺç¾İ
    -0.18
    æĺ¨æĹ¥
    -0.18
    pect
    -0.18
    éĽ¾
    -0.17
     Majority
    -0.17
    ä½ĵ
    -0.17
    POSITIVE LOGITS
    åľ¨åĨħçļĦ
    0.18
    æŁľåı°
    0.18
    prepend
    0.18
    LS
    0.18
    ÑĦин
    0.17
    åľ¨ä¸Ĭæµ·
    0.17
    壮大
    0.17
    -eng
    0.17
    ARY
    0.17
    -Methods
    0.17
    Activations Density 0.335%

    No Known Activations