© 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. 17183
    Prev
    Next
    INDEX
    Explanations

    civil rights and court cases

    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
    Negative Logits
    夫
    -0.23
    豪å®ħ
    -0.20
    ssel
    -0.20
    汶å·Ŀ
    -0.20
    èįī
    -0.19
     Ded
    -0.19
    åģļ梦
    -0.19
     ded
    -0.19
    éĺ¿å¯Įæ±Ĺ
    -0.19
     nostalg
    -0.18
    POSITIVE LOGITS
    é»ijçĻ½
    0.22
    nis
    0.22
    å®ŀæĸ½
    0.20
    ités
    0.19
    ewire
    0.19
    apel
    0.19
    解æĶ¾
    0.19
    è¿Ŀåıį
    0.18
    çŃīå¾ħ
    0.18
    eras
    0.18
    Activations Density 0.014%

    No Known Activations