© 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. 13384
    Prev
    Next
    INDEX
    Explanations

    1-877 numbers

    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
    å°ıçĻ½
    -0.20
    让大家
    -0.20
    èįIJ
    -0.19
    loop
    -0.19
    æĤ¨çļĦåŃ©åŃIJ
    -0.18
    ria
    -0.18
    对åħ¶çľŁå®ŀ
    -0.18
    æĪIJ绩åįķ
    -0.18
    çĻ½è¡£
    -0.18
    seen
    -0.18
    POSITIVE LOGITS
    åīįçŀ»æĢ§
    0.19
    aname
    0.18
    æŀ¢
    0.18
     ÑģÑĤÑĢан
    0.17
    幸
    0.17
    _CLR
    0.17
     compete
    0.17
     ÑģÑĤаÑĤÑĮ
    0.17
    åħ¶ä»ĸåĽ½å®¶
    0.16
    èħĭ
    0.16
    Activations Density 0.002%

    No Known Activations