© 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. 13131
    Prev
    Next
    INDEX
    Explanations

    if not

    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
    s
    -0.24
    ç¾İ丽çļĦ
    -0.22
    è¿Ļä¸ĢåĪ»
    -0.19
    æ¯ıä¸Ģ个
    -0.19
    ä¸Ńæĸ°
    -0.18
    è¿Ļä¸Ģå¹´
    -0.18
    å¦Ĥä»Ĭ
    -0.18
    æ´ĹèĦ¸
    -0.18
    诸å¦Ĥ
    -0.17
    ä¼ŀ
    -0.17
    POSITIVE LOGITS
    eh
    0.20
    lessly
    0.19
    IOD
    0.19
    å°Ĩåħ¶
    0.18
    rastructure
    0.18
    ange
    0.18
    ãģªãģĦ
    0.18
    rames
    0.18
    ï¸
    0.18
    åŃĺåľ¨éĹ®é¢ĺ
    0.17
    Activations Density 0.060%

    No Known Activations