© 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. 14661
    Prev
    Next
    INDEX
    Explanations

    clothing fit

    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
    .chunk
    -0.20
    hti
    -0.19
    巨人
    -0.19
    åѵ
    -0.19
    unks
    -0.18
    èĺĸ
    -0.18
    髯
    -0.18
    æ»Ķ
    -0.18
    emean
    -0.18
    avi
    -0.18
    POSITIVE LOGITS
    tight
    0.25
     tight
    0.23
     tighter
    0.23
    ç´§
    0.22
    å¯Ĩ
    0.21
     Tight
    0.21
     bó
    0.21
    æĶ¶ç´§
    0.21
    ç´§å¯Ĩ
    0.21
    å¼¹æĢ§
    0.20
    Activations Density 0.013%

    No Known Activations