© 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. 12189
    Prev
    Next
    INDEX
    Explanations

    project management and structure

    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
    ç¿»
    -0.23
    èµł
    -0.22
    usu
    -0.21
    æ¿Ģ
    -0.20
    hal
    -0.20
     hal
    -0.20
    æĸ°åŀĭ
    -0.20
     util
    -0.20
    gor
    -0.19
    åİĨåı²æĸ°
    -0.19
    POSITIVE LOGITS
    ä½ĵ系建设
    0.26
    è´¯
    0.24
    ä¿®çĤ¼
    0.23
    æķıæį·
    0.23
    贯穿
    0.23
    éĩijåŃĹå¡Ķ
    0.23
    .metamodel
    0.23
    è§ĦèĮĥ
    0.22
     ISO
    0.22
    ä¿¡æģ¯ç³»ç»Ł
    0.22
    Activations Density 0.058%

    No Known Activations