© 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. 13337
    Prev
    Next
    INDEX
    Explanations

    capable of

    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
    REAM
    -0.18
    elmet
    -0.17
    ãģıãĤĭ
    -0.17
    çıŃ
    -0.16
    yer
    -0.16
    ìłĢ
    -0.16
    .Raise
    -0.16
    el
    -0.16
    ç¾¤å²Ľ
    -0.15
    creen
    -0.15
    POSITIVE LOGITS
    -bodied
    0.24
    ities
    0.23
    è¶³å¤ŁçļĦ
    0.21
    èĥľä»»
    0.19
    ä»İä¸Ń
    0.18
    æĢ§å¼º
    0.18
    éĻIJãĤĬ
    0.18
    ibility
    0.17
    ilities
    0.17
    zech
    0.17
    Activations Density 0.019%

    No Known Activations