© 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. 15732
    Prev
    Next
    INDEX
    Explanations

    sentence boundary punctuation

    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
    讯
    -0.21
    æĸ°ä¸ī
    -0.20
     squirt
    -0.19
    ARB
    -0.19
    _JO
    -0.19
    imed
    -0.18
    ordan
    -0.18
    lice
    -0.18
    Minor
    -0.18
    VR
    -0.17
    POSITIVE LOGITS
    æĺŁåħī
    0.20
    æĭ¥æĬ¤
    0.19
    å¼ĢèĬ±
    0.19
    对ä¸įèµ·
    0.19
    æĭ³
    0.18
     stripslashes
    0.18
    æĺ¯æĪijåĽ½
    0.18
    æķ´ä¸ªäºº
    0.18
    èĢģå¦Ī
    0.18
    ä½łèĩªå·±
    0.18
    Activations Density 0.076%

    No Known Activations