© 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. 13667
    Prev
    Next
    INDEX
    Explanations

    probability of sequences when numbers

    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
     fav
    -0.20
    马ä¸Ĭ
    -0.19
    å±ĭ
    -0.18
    约ä¼ļ
    -0.18
     cou
    -0.18
     Reports
    -0.18
    -alist
    -0.18
    rica
    -0.17
    ady
    -0.17
    ric
    -0.17
    POSITIVE LOGITS
    èĢĻ
    0.21
     Ñıн
    0.19
    æ´ĭ
    0.19
    оÑģоб
    0.18
     crochet
    0.18
    åıijå±ķéĺ¶æ®µ
    0.17
    lap
    0.17
    ÑģпекÑĤ
    0.17
    飶
    0.17
    å·´æĭī
    0.17
    Activations Density 0.038%

    No Known Activations