© 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. 13786
    Prev
    Next
    INDEX
    Explanations

    family and relatives

    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
    ä¸ĭæ²ī
    -0.21
    殿åłĤ
    -0.20
    ä¸įçŁ¥ä¸įè§ī
    -0.20
    çļĦåľ°ä½į
    -0.20
    peat
    -0.20
    享çĶ¨
    -0.20
    èĦ±é¢ĸèĢĮåĩº
    -0.19
     fisheries
    -0.19
     Colbert
    -0.19
     underrated
    -0.19
    POSITIVE LOGITS
    家å±ŀ
    0.26
    亲人
    0.25
    åľ¨æİ¥åıĹ
    0.25
    æĬ¥æ¡Ī
    0.25
    亲å±ŀ
    0.24
    ãģĭãģijãģ¦
    0.23
     ÑĥÑģл
    0.22
    family
    0.22
    äºĭåıij
    0.22
    æİ¥åıĹéĩĩ访
    0.22
    Activations Density 0.044%

    No Known Activations