© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10649
    Prev
    Next
    INDEX
    Explanations

    clothing and attire

    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
    å¾Īä¸įéĶĻ
    -0.24
    èĥ«
    -0.23
    æī©å¼ł
    -0.22
    å¾Īåĸľæ¬¢
    -0.20
    å°±å¾Ī
    -0.20
    å½Ĵå±ŀ
    -0.20
     Crunch
    -0.19
    æĭĬ
    -0.19
    æIJ¬å®¶
    -0.19
    hack
    -0.19
    POSITIVE LOGITS
    åIJĦèĩª
    0.25
    iet
    0.22
    åIJĦèĩªçļĦ
    0.21
    odus
    0.21
    lm
    0.21
    await
    0.20
    ä½³
    0.20
    SCAN
    0.19
     respective
    0.19
     appreciation
    0.18
    Activations Density 0.012%

    No Known Activations