© 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. 12845
    Prev
    Next
    INDEX
    Explanations

    amount 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
    主ä¹ī
    -0.20
    commons
    -0.19
    (of
    -0.18
    åĮĸ身
    -0.18
    agers
    -0.18
    iated
    -0.18
    夫
    -0.18
    изм
    -0.17
    ager
    -0.17
    nano
    -0.17
    POSITIVE LOGITS
    лем
    0.19
    ê»ı
    0.18
    æľīå¤ļå°ij
    0.18
    ä¸Ĭåīį
    0.18
    piel
    0.18
     ÑĢеалÑĮно
    0.18
     Cra
    0.17
     available
    0.17
    /how
    0.17
    uale
    0.17
    Activations Density 0.075%

    No Known Activations