© 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. 11014
    Prev
    Next
    INDEX
    Explanations

    careers in

    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
     зад
    -0.22
    burst
    -0.19
    onian
    -0.18
    اصة
    -0.18
     bulund
    -0.18
    æģĥ
    -0.18
    äºļåĨĽ
    -0.18
    åĩłæ¬¡
    -0.17
    åĻ¨
    -0.17
    æ¯ıä¸Ģ
    -0.17
    POSITIVE LOGITS
    èģĮä¸ļ
    0.20
    çļĭ
    0.20
    osen
    0.20
    åħīèį£
    0.19
    è¿Ļ个èģĮä¸ļ
    0.19
    ongan
    0.19
    翱
    0.19
    æĬķ身
    0.18
    umbing
    0.18
    _gray
    0.18
    Activations Density 0.024%

    No Known Activations