© 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. 15331
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    OPS
    -0.20
    羣缸
    -0.19
    mps
    -0.18
    æķ´ä¸ªäºº
    -0.18
    大äºĭ
    -0.17
    骺
    -0.17
    åħ¨éĿ¢åıijå±ķ
    -0.17
    çľĭçĤ¹
    -0.17
    æİĴåIJį第
    -0.17
    å¾Īå¤ļäºĭæĥħ
    -0.17
    POSITIVE LOGITS
    ä¸Ģå®ļçļĦ
    0.22
     огÑĢани
    0.20
    é¢Ŀå¤ĸ
    0.19
    åĩĨåħ¥
    0.19
    éĻĦåĬł
    0.19
    éĺ¶æ¢¯
    0.19
    éĹ¨æ§Ľ
    0.19
    icensing
    0.19
    æĹłæķĪ
    0.19
    éĻIJ
    0.18
    Activations Density 0.036%

    No Known Activations