© 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. 17249
    Prev
    Next
    INDEX
    Explanations

    class name or variable `foo`

    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
    æĪ¾
    -0.20
    appe
    -0.18
    æĢ§åĴĮ
    -0.18
    SED
    -0.18
    çļĦå°±æĺ¯
    -0.18
     sprayed
    -0.18
    ng
    -0.18
    è¿ĺæĺ¯å¾Ī
    -0.17
    ç¿»å¼Ģ
    -0.17
    è¸ī
    -0.17
    POSITIVE LOGITS
    ä¾ĭå¤ĸ
    0.19
    å¨ģå°Ķ
    0.19
    éĢĶä¸Ń
    0.19
    çĶº
    0.18
    rosse
    0.18
    ivor
    0.18
     nullable
    0.17
    į°
    0.17
    TOOLS
    0.17
     dist
    0.17
    Activations Density 0.015%

    No Known Activations