© 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. 14039
    Prev
    Next
    INDEX
    Explanations

    "I" followed by common sentence starters

    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
    åĽ´çĿĢ
    -0.21
    bsp
    -0.20
    æĽ´éĩįè¦ģçļĦ
    -0.19
    hel
    -0.19
    edit
    -0.19
    è¿ĺæľīå¾Īå¤ļ
    -0.18
    墩
    -0.18
    name
    -0.18
     arrayOf
    -0.18
    Edit
    -0.18
    POSITIVE LOGITS
    åħ¶å®ŀ
    0.22
    éĤ£æĺ¯
    0.21
    ä¹Łä¸į
    0.21
    ogui
    0.21
    æĪijæĥ³
    0.21
    rawid
    0.21
     actually
    0.20
     ÐIJлекÑģан
    0.20
    AUSE
    0.20
     ÐĶмиÑĤÑĢ
    0.20
    Activations Density 0.074%

    No Known Activations