© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10792
    Prev
    Next
    INDEX
    Explanations

    Long .js / io

    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
    Not in Any Lists

    No Comments

    Negative Logits
    人æ°Ķ
    -0.22
    è·ª
    -0.19
    æIJŃ
    -0.19
    糯
    -0.19
    ä¸Ģç»ı
    -0.19
     Harness
    -0.18
    pret
    -0.18
    .heroku
    -0.17
    CONDS
    -0.17
    outu
    -0.17
    POSITIVE LOGITS
    ize
    0.19
     juni
    0.19
     ipsum
    0.18
    ablo
    0.18
    bild
    0.18
    izational
    0.18
    isations
    0.17
    ÙĪج
    0.17
    驹
    0.17
     OLED
    0.17
    Activations Density 0.002%

    No Known Activations