© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16956
    Prev
    Next
    INDEX
    Explanations

    may not use

    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
    èĥ½æĬĬ
    -0.24
    èĥ½åģļåĪ°
    -0.23
    èĥ½å¾ĹåĪ°
    -0.20
    èĥ½å¤Łè®©
    -0.20
    èĥ½è®©
    -0.20
     maybe
    -0.19
    æĪijçŁ¥éģĵ
    -0.19
    äºĨä¸Ģéģį
    -0.18
    èĥ½çľĭåĪ°
    -0.18
    åĽłä¸ºå®ĥ
    -0.18
    POSITIVE LOGITS
    åij£
    0.22
    æĥħ趣
    0.22
    ä¹ŁåºĶ该
    0.22
    nard
    0.21
    大èĩ´
    0.20
    ä»»ä½ķæŶåĢĻ
    0.20
    oola
    0.20
    ields
    0.19
    alties
    0.19
    ä¹Łåı¯èĥ½
    0.19
    Activations Density 0.145%

    No Known Activations