© 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. 10537
    Prev
    Next
    INDEX
    Explanations

    CD and cell counts

    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
    /effects
    -0.19
    ittings
    -0.18
    etto
    -0.18
    stück
    -0.18
    &r
    -0.18
    éĻª
    -0.18
    çĤ¼
    -0.17
    wares
    -0.17
     revolving
    -0.17
    çĵ¦
    -0.17
    POSITIVE LOGITS
    é«ĵ
    0.22
    大åĨĽ
    0.20
    ged
    0.20
    ŀæĢ§
    0.18
    è¢Ī
    0.17
    ivitÃł
    0.17
    uell
    0.17
    è¿Ļå¼ł
    0.17
    é²ľæĺİ
    0.17
    éĺ³æĢ§
    0.17
    Activations Density 0.101%

    No Known Activations