© 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. 13244
    Prev
    Next
    INDEX
    Explanations

    comprehension

    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
    èĬ±æł·
    -0.19
    teenth
    -0.17
    æĸ°åŁİ
    -0.17
    ãģ£ãģ±
    -0.17
    uate
    -0.16
    apsed
    -0.16
    wards
    -0.16
    æĭĪ
    -0.16
    urious
    -0.16
    .PLL
    -0.16
    POSITIVE LOGITS
    ems
    0.18
    æѤäºĭ
    0.17
    æĪļ
    0.17
     unsur
    0.17
    eur
    0.17
    ibility
    0.16
    ive
    0.16
    ä¸įäºĨ
    0.16
    ionate
    0.16
    èı½
    0.16
    Activations Density 0.016%

    No Known Activations