© 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. 13192
    Prev
    Next
    INDEX
    Explanations

    prediction and prediction rules

    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
    sterdam
    -0.16
    ickey
    -0.16
    ayed
    -0.16
    ilton
    -0.15
    enge
    -0.15
    èĩ¾
    -0.15
    ëģĶ
    -0.15
    /light
    -0.15
    culate
    -0.15
    puty
    -0.15
    POSITIVE LOGITS
    ions
    0.22
    ive
    0.20
    ably
    0.19
    æĢ§å¼º
    0.18
    æĢ§çļĦ
    0.18
    é¢ĦæĬ¥
    0.18
    nel
    0.17
    /pre
    0.17
    ively
    0.17
    icates
    0.17
    Activations Density 0.055%

    No Known Activations