© 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. 17030
    Prev
    Next
    INDEX
    Explanations

    code return statements

    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
    导
    -0.21
    ç¥ŀ
    -0.21
    åħ¬
    -0.20
     Terrace
    -0.20
    ï¼Ī
    -0.20
    AR
    -0.19
    æĽ²
    -0.19
    posing
    -0.19
    寸
    -0.19
    å¤ı天
    -0.19
    POSITIVE LOGITS
    第ä¸ī次
    0.25
    åĨį次
    0.23
    æŀĭ
    0.22
    åĨįä¸Ģ次
    0.21
    天é¹ħ
    0.20
    again
    0.20
    çĭIJçĭ¸
    0.20
    æĺŁçº§éħĴåºĹ
    0.20
    noch
    0.20
     again
    0.20
    Activations Density 0.002%

    No Known Activations