© 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. 10364
    Prev
    Next
    INDEX
    Explanations

    filelicensesite

    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
    SÄ°
    -0.20
    PropertyParams
    -0.20
    prm
    -0.19
    棱
    -0.18
    XD
    -0.18
    .execution
    -0.17
    æĽ©
    -0.17
    osi
    -0.17
    .Fat
    -0.17
    /questions
    -0.17
    POSITIVE LOGITS
    ä¹Łåı¯
    0.23
    çļĦè¯Ŀè¯Ń
    0.22
    æŃ¤ä¸¾
    0.22
    çľģåĨħ
    0.21
    ä¹Łåı¯ä»¥
    0.20
    ä¸Ģç»ı
    0.20
    亲åĪĩ
    0.20
    ä¹Łä¼ļ
    0.19
    located
    0.19
    éĢĶä¸Ń
    0.19
    Activations Density 0.071%

    No Known Activations