© 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. 16224
    Prev
    Next
    INDEX
    Explanations

    question or colon

    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
    å¸ĪåĤħ
    -0.19
    acro
    -0.18
    åı¦è¡Į
    -0.17
    æµ·å²Ľ
    -0.17
    缸
    -0.17
     wirk
    -0.17
    æĭīä¸ģ
    -0.17
    èĴ²
    -0.17
    bru
    -0.17
    cae
    -0.16
    POSITIVE LOGITS
    主è¦ģæĺ¯
    0.22
    大大å°ıå°ı
    0.20
    éĿŀåĩ¡
    0.19
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.19
    åıijçĶŁäºĨ
    0.18
    sst
    0.18
    ä¸ĬéĿ¢
    0.18
    ÃŃst
    0.18
     trách
    0.18
    åĩĩ
    0.18
    Activations Density 0.042%

    No Known Activations