© 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. 14144
    Prev
    Next
    INDEX
    Explanations

    felony misdemeanor

    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
    ness
    -0.20
    çłĶåıijæĬķåħ¥
    -0.18
    æĭ½
    -0.18
    åį«è§Ĩ
    -0.18
    ãĥķãĤ¡
    -0.17
    å°ıæŶåĢĻ
    -0.17
    åī§ä¸Ń
    -0.17
    sword
    -0.17
    ä¼ĺç§ĢçļĦ
    -0.16
    å¾Ī好çļĦ
    -0.16
    POSITIVE LOGITS
    lege
    0.20
    ments
    0.19
    ewolf
    0.19
    (@(
    0.19
    çıī
    0.18
    ry
    0.18
    èĸ®
    0.18
     ìķĦëĭĮ
    0.17
    alytics
    0.17
     sized
    0.17
    Activations Density 0.004%

    No Known Activations