© 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. 11027
    Prev
    Next
    INDEX
    Explanations

    quantities of people, deaths, or casualties

    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
    æĻ®åıĬ
    -0.21
    ä¸ĭ次
    -0.20
     дог
    -0.20
    inet
    -0.18
    ä¸Ģè¡Į
    -0.18
     Stem
    -0.18
    è¶ĬæĿ¥è¶Ĭ大
    -0.18
    esc
    -0.18
    åĮºåĪĨ
    -0.18
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.18
    POSITIVE LOGITS
    å¼ĢèįĴ
    0.24
    åĵĨ
    0.22
    åħ¶ä¸ŃåĮħæĭ¬
    0.22
    ä¸ī代
    0.22
    çĸijä¼¼
    0.21
    è¿Ļ段æŶéĹ´
    0.21
    失踪
    0.21
    éªļ
    0.20
    yro
    0.20
    æ´Ļ
    0.20
    Activations Density 0.039%

    No Known Activations