© 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. 13035
    Prev
    Next
    INDEX
    Explanations

    recipe notes

    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
    éļĪ
    -0.21
    ply
    -0.19
    emento
    -0.18
    seg
    -0.18
    -disc
    -0.18
     lag
    -0.18
    inium
    -0.18
    plementary
    -0.18
    iated
    -0.18
    disc
    -0.17
    POSITIVE LOGITS
    大åħ¨
    0.25
    çªį
    0.24
    åģļé¥Ń
    0.22
    åģļæ³ķ
    0.21
     recipe
    0.21
    羸
    0.21
    çļĦåģļæ³ķ
    0.21
    æİĴåIJį第
    0.20
    åIJĦè¡Į
    0.20
    ç´łé£Ł
    0.20
    Activations Density 0.019%

    No Known Activations