© 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. 13142
    Prev
    Next
    INDEX
    Explanations

    xhtml doctype declarations

    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
    ä»ĩ
    -0.20
    æĿĤ
    -0.20
    æĢ¨
    -0.20
    å«Į
    -0.19
    第ä¸ī
    -0.19
    urat
    -0.19
    ä¸ĭæīĭ
    -0.19
    æĢ»ä½ĵè§ĦåĪĴ
    -0.18
    otal
    -0.18
     THIRD
    -0.18
    POSITIVE LOGITS
    æ²½
    0.20
     лÑİбой
    0.19
     Vine
    0.19
    åij¼
    0.18
    ä¿¡ç®±
    0.18
     Neal
    0.18
    æ±
    0.17
     Marino
    0.17
     Tart
    0.17
    icious
    0.17
    Activations Density 0.054%

    No Known Activations