© 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. 12016
    Prev
    Next
    INDEX
    Explanations

    Modified, updated, filed dates

    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
    ä¸īæĸ¹
    -0.20
    æĥ³å¿µ
    -0.19
    éĩį大
    -0.19
     моÑīн
    -0.18
    è¶Ĭ好
    -0.18
    è´Ŀ
    -0.17
    æĹłåģ¿
    -0.17
    индив
    -0.17
    bon
    -0.17
    iram
    -0.17
    POSITIVE LOGITS
    ков
    0.22
    boom
    0.20
    çĤĻ
    0.19
    ä¸ĢåĽŀäºĭ
    0.19
    ä¸Ģ件äºĭ
    0.18
    PathComponent
    0.18
    ä¸ĭåįĬåľº
    0.18
    çįł
    0.18
    ä¸Ģéĺµ
    0.17
    æŃ¥åħ¥
    0.17
    Activations Density 0.005%

    No Known Activations