© 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. 16986
    Prev
    Next
    INDEX
    Explanations

    fin, sail, or stabilizer

    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
    åľ°éģĵ
    -0.20
    å°Ħæīĭ
    -0.20
    JNIEnv
    -0.19
    箪
    -0.19
    berman
    -0.19
    ç¬ij声
    -0.19
    æīĵéĢļ
    -0.19
    arov
    -0.19
    appings
    -0.19
    æĢľ
    -0.18
    POSITIVE LOGITS
    less
    0.24
    çīĩ
    0.21
    建åįİ
    0.20
    设计
    0.20
    å½¢çĬ¶
    0.20
     shaped
    0.20
     shape
    0.20
     sail
    0.19
    å°ĸ
    0.19
     fins
    0.19
    Activations Density 0.012%

    No Known Activations