© 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. 17230
    Prev
    Next
    INDEX
    Explanations

    countries

    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
    èĪµ
    -0.19
     shedding
    -0.19
    _emit
    -0.19
    |#
    -0.19
     sails
    -0.18
    rove
    -0.18
    reater
    -0.18
    èĩªæŁ¥
    -0.17
    棹
    -0.17
    ró
    -0.17
    POSITIVE LOGITS
    çķĻåѦ
    0.25
     gig
    0.22
    åħ¥å¢ĥ
    0.22
    è¿ĩå¹´
    0.21
    度è¿ĩ
    0.21
    å¾Īå¤ļäºĭæĥħ
    0.20
    éĢļè¡Įè¯ģ
    0.20
    çĶŁæ´»ä¹łæĥ¯
    0.20
    çľģéĴ±
    0.20
    åIJĦè¡ĮåIJĦä¸ļ
    0.20
    Activations Density 0.074%

    No Known Activations