© 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. 16455
    Prev
    Next
    INDEX
    Explanations

    disclaimers

    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
    举
    -0.22
    夺
    -0.21
    å®Ĺ
    -0.20
    æľī两个
    -0.20
    æł·åŃIJ
    -0.20
    uran
    -0.19
    æľīåĩłä¸ª
    -0.19
    èIJİ缩
    -0.19
    æĮģä¹ħ
    -0.19
    SS
    -0.19
    POSITIVE LOGITS
    ä¸į代表
    0.26
    æĦıè¦ĭ
    0.21
    æŃī
    0.20
     ÑģамоÑģÑĤоÑı
    0.19
     каÑĩеÑģÑĤво
    0.19
    è¨Ģ论
    0.19
    âĪľ
    0.18
    .Angle
    0.18
    ILER
    0.18
    utf
    0.18
    Activations Density 0.046%

    No Known Activations