© 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. 16273
    Prev
    Next
    INDEX
    Explanations

    months

    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
    羸
    -0.19
    ç¶ļ
    -0.18
    å¹³æŶ
    -0.18
    yer
    -0.17
    éĻĤ
    -0.17
     lunches
    -0.17
     PaÅĦstwo
    -0.17
    åĴĮæľįåĬ¡
    -0.17
    äºĨä¸Ģåı£
    -0.17
    nf
    -0.16
    POSITIVE LOGITS
    以ä¾Ĩ
    0.22
    -long
    0.21
     меÑģÑı
    0.21
     ayında
    0.19
     اÙĦÙħاضÙĬ
    0.19
    æľĶ
    0.19
    /month
    0.19
    -ending
    0.19
    -ish
    0.18
    æŁIJ
    0.18
    Activations Density 0.196%

    No Known Activations