© 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. 10330
    Prev
    Next
    INDEX
    Explanations

    tool chuck assemblies

    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
    Vien
    -0.17
     Ä°l
    -0.16
    èı½
    -0.15
    roscope
    -0.15
    agli
    -0.15
    ió
    -0.14
    earch
    -0.14
    sing
    -0.14
    utilus
    -0.14
    .metamodel
    -0.14
    POSITIVE LOGITS
    chain
    0.21
    kits
    0.21
    æĢ§å¼º
    0.19
    tips
    0.19
    chest
    0.18
    åĵĩ
    0.17
    scan
    0.17
    é½IJåħ¨
    0.17
    ç®±
    0.16
    manship
    0.16
    Activations Density 0.045%

    No Known Activations