© 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. 16711
    Prev
    Next
    INDEX
    Explanations

    business reputation or groups

    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
    å«ķ
    -0.21
    æݧèĤ¡éĽĨåĽ¢
    -0.20
    讽
    -0.20
     Poster
    -0.20
    listeners
    -0.19
     Rent
    -0.19
     ourselves
    -0.19
    modifiable
    -0.19
    Æ°á»Ľ
    -0.19
    çĵ»
    -0.19
    POSITIVE LOGITS
    æĪĸèĢħ
    0.28
    è·Łä½ł
    0.25
    èµ·çłģ
    0.25
     reputable
    0.23
     or
    0.23
    æĪĸ
    0.23
    åħ¬å¸ĥçļĦ
    0.23
    è·
    0.23
    ä»ĸ们
    0.23
    æĪĸèĢħæĺ¯
    0.22
    Activations Density 0.030%

    No Known Activations