© 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. 16576
    Prev
    Next
    INDEX
    Explanations

    down or up

    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
     Raqqa
    -0.20
    à¸Ħà¸ĵะà¸ģรรม
    -0.19
     Kurds
    -0.18
     à¹Ģมษ
    -0.18
     Rohing
    -0.18
     Bam
    -0.18
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.17
    æĢģ
    -0.17
     nặng
    -0.17
     Unidos
    -0.16
    POSITIVE LOGITS
    ä¸ĢæĿ¡
    0.25
    cuts
    0.23
    ä¸Ģæ¢Ŀ
    0.22
    产ä¸ļéĵ¾
    0.20
    ways
    0.20
    /down
    0.20
    éĺ¶æ¢¯
    0.19
    line
    0.19
    river
    0.19
    åİĨåı²æĤłä¹ħ
    0.19
    Activations Density 0.016%

    No Known Activations