© 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. 17078
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    请åıĬæŶ
    -0.21
    åīŁ
    -0.20
    tel
    -0.19
    opro
    -0.19
    ä¹ĭäºĭ
    -0.18
    âĩĿ
    -0.18
    _unused
    -0.18
    ati
    -0.17
    rollers
    -0.17
    erator
    -0.17
    POSITIVE LOGITS
     heat
    0.21
    ÑĤов
    0.21
    çīĪæĿĥ
    0.20
    ific
    0.19
     sand
    0.19
    ãģĿ
    0.19
    åįģåĽĽ
    0.19
    åĤį
    0.18
     accred
    0.18
    è½»
    0.18
    Activations Density 0.000%

    No Known Activations