© 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. 14029
    Prev
    Next
    INDEX
    Explanations

    prime example or candidate

    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
    akes
    -0.20
    å¥ĩ迹
    -0.20
    ople
    -0.18
    ahu
    -0.18
    asco
    -0.18
    Reality
    -0.17
    apo
    -0.17
    åĵį
    -0.17
    odie
    -0.17
     miracles
    -0.17
    POSITIVE LOGITS
    æĹ¶æ®µ
    0.22
    æĹłæ¯Ķ
    0.22
    åľ°æ®µ
    0.22
    ä¹ĭåľ°
    0.20
    æĹ¶æľº
    0.20
    åħ¸åŀĭçļĦ
    0.19
    ä¹ĭä½ľ
    0.19
    èİ«è¿ĩäºİ
    0.19
    éĥ¨ä½į
    0.19
    人èĦī
    0.19
    Activations Density 0.014%

    No Known Activations