© 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. 16457
    Prev
    Next
    INDEX
    Explanations

    prices, pricing, rates, costs

    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
    ument
    -0.20
    æĹłæķ°æ¬¡
    -0.20
    tober
    -0.19
    antically
    -0.19
    ause
    -0.18
    dess
    -0.18
    pras
    -0.18
    qual
    -0.18
    æ¯Ĺ
    -0.18
     countless
    -0.17
    POSITIVE LOGITS
    详æĥħ
    0.27
    åıĸåĨ³äºİ
    0.26
    tables
    0.23
    è¡Įæĥħ
    0.23
    åIJĦå¼Ĥ
    0.23
    bles
    0.23
    rates
    0.23
    æł¹æį®ä¸įåIJĮ
    0.23
    æĺ¯å¤ļå°ij
    0.23
    æĥħåĨµ
    0.22
    Activations Density 0.025%

    No Known Activations