© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15115
    Prev
    Next
    INDEX
    Explanations

    initialisms

    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
     vot
    -0.23
    åĮº
    -0.19
    åľĨ
    -0.19
    idx
    -0.18
    åĥı
    -0.18
     jungle
    -0.18
    py
    -0.18
    èĽĬ
    -0.18
     dup
    -0.18
    çıŃ级
    -0.18
    POSITIVE LOGITS
    	RTLR
    0.25
    	TokenName
    0.20
    oten
    0.19
    senal
    0.19
    ç»ıèIJ¥æ´»åĬ¨
    0.19
    /stats
    0.19
    第äºĮ大
    0.19
    etur
    0.19
    numerusform
    0.19
    çļĦ人æĿ¥è¯´
    0.19
    Activations Density 0.405%

    No Known Activations