© 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. 17076
    Prev
    Next
    INDEX
    Explanations

    non-

    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
    Negative Logits
    ç¼Ĩ
    -0.23
    åĶ¯
    -0.21
    ä¸įå¿ĺåĪĿå¿ĥ
    -0.19
    产ä¸ļæī¶è´«
    -0.19
    åıijå¸ĥæŶéĹ´
    -0.19
    è·Ľ
    -0.19
    åīįçŀ»
    -0.19
    åħģ
    -0.18
    PageIndex
    -0.18
    对æİ¥
    -0.18
    POSITIVE LOGITS
    (non
    0.23
    /non
    0.23
    éĻĮçĶŁ
    0.22
     дело
    0.21
    é½
    0.21
    ãģ¾ãģ¾
    0.21
    éĻĮ
    0.20
    ä¸įäºĨ解
    0.20
     yet
    0.20
    çĬ¶æĢģä¸ĭ
    0.19
    Activations Density 0.096%

    No Known Activations