© 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. 15560
    Prev
    Next
    INDEX
    Explanations

    product descriptions

    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
    çıŃ
    -0.19
    çºł
    -0.19
     relegated
    -0.19
    getLast
    -0.18
    lops
    -0.18
    apel
    -0.18
    avery
    -0.17
     Pon
    -0.17
     slog
    -0.17
     Dum
    -0.17
    POSITIVE LOGITS
    Disclosure
    0.20
    éĶ·
    0.19
    ç¯Ļ
    0.19
    adian
    0.19
    /product
    0.19
    EMON
    0.18
    оÑħÑĢан
    0.18
    ìĽĥ
    0.18
    æľ¬èº«çļĦ
    0.18
    emon
    0.18
    Activations Density 0.025%

    No Known Activations