© 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. 10415
    Prev
    Next
    INDEX
    Explanations

    encoding metadata

    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
     pa
    -0.21
    grim
    -0.19
    æ§Į
    -0.19
    UID
    -0.18
    pa
    -0.18
    variably
    -0.18
    æݧ
    -0.17
    mand
    -0.17
    '/
    -0.17
     gu
    -0.17
    POSITIVE LOGITS
    erator
    0.21
    ä¸ĭåįĬ
    0.20
     strapon
    0.20
    alsex
    0.18
    ç½ijé¦ĸ页
    0.18
    TabIndex
    0.18
     echang
    0.18
     danmark
    0.18
     spep
    0.17
    ozo
    0.17
    Activations Density 0.034%

    No Known Activations