© 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. 10410
    Prev
    Next
    INDEX
    Explanations

    misunderstanding, misconception, misuse

    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
    tering
    -0.22
    umer
    -0.19
    ä¸įåħĭ
    -0.17
    uator
    -0.17
    .opensource
    -0.17
    íŀĪ
    -0.16
    ä¸įä½ı
    -0.16
    示èĮĥåŁºåľ°
    -0.16
    çĩİ
    -0.16
    å¾Īæĺ¯
    -0.16
    POSITIVE LOGITS
    ellaneous
    0.25
    /conf
    0.21
    /un
    0.21
    å·²ä¹ħçļĦ
    0.20
    ingly
    0.20
    Occurred
    0.19
    /il
    0.18
    ably
    0.18
    /no
    0.18
     expectations
    0.18
    Activations Density 0.034%

    No Known Activations