© 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. 16992
    Prev
    Next
    INDEX
    Explanations

    homocysteine or related "-cysteine" words

    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
    -none
    -0.20
     Banc
    -0.19
    豪éŨ
    -0.19
    _ta
    -0.18
    leans
    -0.18
    efs
    -0.18
     бан
    -0.17
    ä¸ī家
    -0.17
     coast
    -0.17
     Coast
    -0.17
    POSITIVE LOGITS
    owie
    0.20
    èģĮæĿĥ
    0.19
    æ£īèĬ±
    0.19
    éĽªèĬ±
    0.19
    ç²ī
    0.19
    icap
    0.19
    æī
    0.18
    éĴ¼
    0.18
    å°ĺ
    0.18
    eve
    0.18
    Activations Density 0.006%

    No Known Activations