© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15108
    Prev
    Next
    INDEX
    Explanations

    amputation or prosthetics

    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
    gmail
    -0.22
    arden
    -0.22
    ockey
    -0.18
    itage
    -0.18
    riting
    -0.18
    æij¹
    -0.18
    usband
    -0.18
    curity
    -0.17
    社ä¼ļ责任
    -0.17
    riter
    -0.17
    POSITIVE LOGITS
    META
    0.19
    planes
    0.19
    èıĬ
    0.18
    ãĤµãĥĿãĥ¼ãĥĪ
    0.18
    ÑĢоÑģ
    0.17
    æ³¾
    0.17
     Liga
    0.17
    ÙĦÙĬÙĥ
    0.17
    åīįæīĢ
    0.17
    åĪĢ
    0.17
    Activations Density 0.005%

    No Known Activations