© 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. 17143
    Prev
    Next
    INDEX
    Explanations

    bio- prefix followed by 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
    Negative Logits
    edException
    -0.20
    à¹Į
    -0.19
    ãģĦãģ¾ãģĻ
    -0.18
    oup
    -0.15
    alom
    -0.15
     à¹Ĩ
    -0.15
    unch
    -0.15
    ãĤĪãģĨãģ«
    -0.15
    asco
    -0.15
    iple
    -0.15
    POSITIVE LOGITS
    posite
    0.19
    CEED
    0.17
    icients
    0.17
    åŃ¦å®¶
    0.16
    rist
    0.16
    utions
    0.16
    ponent
    0.15
    ject
    0.15
    ī
    0.15
    -minded
    0.15
    Activations Density 0.037%

    No Known Activations