© 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. 13905
    Prev
    Next
    INDEX
    Explanations

    note that / note,

    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
    ãģ¾ãģļãģ¯
    -0.20
    Descriptors
    -0.19
    oman
    -0.19
    calar
    -0.18
    æŀ¶
    -0.17
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.17
    AndView
    -0.17
    æݢ索
    -0.17
    enas
    -0.17
     ìĿ´ë¥¼
    -0.17
    POSITIVE LOGITS
    ä¿Ŀ管
    0.21
    ä¹Łä¸įè¦ģ
    0.20
    åįĥä¸ĩä¸įè¦ģ
    0.19
    æľīä¸ĢçĤ¹
    0.19
    cation
    0.18
    ä¸įç®¡ä½ł
    0.18
     cultiv
    0.16
    åĩłçĤ¹
    0.16
    IDO
    0.16
    åĪ©çĽĬ
    0.16
    Activations Density 0.005%

    No Known Activations