© 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. 11810
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    人æ°ijæĶ¿åºľ
    -0.21
     doubtful
    -0.20
    éļ¾å¾Ĺ
    -0.20
    ç°ĩ
    -0.20
    ä¸įå¿ĺ
    -0.20
    irl
    -0.19
    SEX
    -0.19
    æĻ®æĥł
    -0.19
    ä¸įéĶĻçļĦ
    -0.18
    æľīæľĽ
    -0.18
    POSITIVE LOGITS
    æīĵåĩ»
    0.34
    æįŁå¤±
    0.26
    æİīäºĨ
    0.25
    éĻįåĪ°
    0.24
    ç»ıæµİæįŁå¤±
    0.23
    éĻįå¹ħ
    0.23
    è´Ł
    0.23
     loss
    0.23
     bait
    0.22
    =(-
    0.22
    Activations Density 0.361%

    No Known Activations