© 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. 13253
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    æ¹®
    -0.21
     bon
    -0.21
    帽åŃIJ
    -0.19
    åij¼åĴĮ
    -0.19
    áĥ«
    -0.19
    егод
    -0.18
    çļĭ
    -0.17
    íı´
    -0.17
    erras
    -0.17
    æ©Ħ
    -0.17
    POSITIVE LOGITS
     Reviewed
    0.23
    示
    0.20
    Verified
    0.19
    çļĦé£İéĻ©
    0.19
    ç»Ĩèĩ´
    0.19
    æİĴæŁ¥
    0.19
     Verified
    0.19
     INCLUDED
    0.18
    æ½®
    0.18
    ç»ĨåĮĸ
    0.18
    Activations Density 0.018%

    No Known Activations