© 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. 11562
    Prev
    Next
    INDEX
    Explanations

    line axis is

    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
    _substr
    -0.23
     kla
    -0.21
    éļĽ
    -0.20
    ä»įæľī
    -0.19
    ä¸Ńä»ĭ
    -0.18
    ä¹ĭæĺŁ
    -0.18
    æľ¬èº«çļĦ
    -0.18
    _comparison
    -0.18
    анÑĤ
    -0.18
    ZW
    -0.18
    POSITIVE LOGITS
    æĺ¯æĪijçļĦ
    0.29
    çļĦå°±æĺ¯
    0.27
    éĥ¨ä»½
    0.25
    æĺ¯æĪij
    0.25
    åĪĻæĺ¯
    0.25
    æĺ¯ä»ĸ
    0.24
    便æĺ¯
    0.24
    æĺ¯åĽ½åĨħ
    0.24
    æĺ¯æĪij们
    0.24
    å°±æĺ¯
    0.24
    Activations Density 0.083%

    No Known Activations