© 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. 12920
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. CA

    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
    %c
    -0.19
     DVD
    -0.19
    æİĮæı¡
    -0.19
    çİĭåĽ½
    -0.19
    Sdk
    -0.19
     Kitt
    -0.18
    ida
    -0.18
    éĩijå±±
    -0.18
    å¤§åĽ½
    -0.17
     Katz
    -0.17
    POSITIVE LOGITS
    åŃĹ第
    0.30
    ä¸Ģåı·
    0.28
    å±Ĥåĩº
    0.19
    åħį
    0.18
    æģ£
    0.18
    áln
    0.18
    validators
    0.18
     cushion
    0.18
    åĿ³
    0.18
    笺
    0.18
    Activations Density 0.216%

    No Known Activations