© 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. 11504
    Prev
    Next
    INDEX
    Explanations

    initials and abbreviations

    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
     morale
    -0.18
    èī®
    -0.17
    DISABLE
    -0.17
     FEATURE
    -0.17
     bull
    -0.17
    æĪĸæĺ¯
    -0.17
     slap
    -0.17
    ACTION
    -0.17
     (++
    -0.17
    demo
    -0.17
    POSITIVE LOGITS
    itable
    0.21
     Young
    0.20
     Jr
    0.20
    -wow
    0.20
    Began
    0.19
    æ¤ħ
    0.19
     Wit
    0.19
    个åĪ«
    0.18
    è·Łä¸įä¸Ĭ
    0.17
    æľīçĶ¨çļĦ
    0.17
    Activations Density 0.054%

    No Known Activations