© 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. 14668
    Prev
    Next
    INDEX
    Explanations

    political parties and movements

    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
    è¿Ļæĸ¹éĿ¢
    -0.25
    æīĵãģ¡
    -0.22
    åģļå·¥
    -0.21
     пÑĢедназнаÑĩен
    -0.20
    æīĵæī°
    -0.19
    åĪ©æ¶¦çİĩ
    -0.19
    çĶŁæ´»çݯå¢ĥ
    -0.19
    æ®´
    -0.19
    Translated
    -0.19
     DispatchQueue
    -0.18
    POSITIVE LOGITS
    æ´¾
    0.22
    浪潮
    0.22
    æīĭä¸ŃçļĦ
    0.21
    avid
    0.21
    æĹĹ
    0.21
    æĹĹå¸ľ
    0.21
    sher
    0.21
    tsy
    0.20
    ismo
    0.20
    åŤ
    0.19
    Activations Density 0.004%

    No Known Activations