© 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. 17103
    Prev
    Next
    INDEX
    Explanations

    anonymous, masking, protection

    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
    è·µ
    -0.20
    Exclusive
    -0.19
    æ¸ħçIJĨ
    -0.19
    å®ģéĿĻ
    -0.19
    elin
    -0.19
    åģľå·¥
    -0.18
    æĺİåªļ
    -0.18
    èī¯
    -0.18
    halt
    -0.18
    åĪĨæł¡
    -0.18
    POSITIVE LOGITS
    åĮ¿åIJį
    0.38
     anonymity
    0.35
    anonymous
    0.33
     anonymous
    0.33
    Anonymous
    0.32
     Anonymous
    0.28
    onym
    0.28
     anonym
    0.26
     anon
    0.25
    身份
    0.25
    Activations Density 0.030%

    No Known Activations