© 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. 13651
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ï¸ı
    -0.23
    تÙħر
    -0.18
    amp
    -0.18
    âĢ³
    -0.17
     &
    -0.17
    éĩijéĴ±
    -0.17
    ../
    -0.16
    NullOr
    -0.16
     amp
    -0.16
     Hale
    -0.16
    POSITIVE LOGITS
    -two
    0.21
    fold
    0.20
    /th
    0.20
    ths
    0.20
     ÐŁÐ¾Ñĩем
    0.19
    -six
    0.19
     ÐIJлекÑģан
    0.17
     atrás
    0.17
    edly
    0.17
    -nine
    0.17
    Activations Density 0.136%

    No Known Activations