© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13593
    Prev
    Next
    INDEX
    Explanations

    time schedule

    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
    etten
    -0.22
    .CG
    -0.21
     upside
    -0.19
     Bison
    -0.19
    .Publish
    -0.19
    anko
    -0.19
     Quarterly
    -0.19
    ccount
    -0.18
    èļĤèļģ
    -0.18
    èľĺèĽĽ
    -0.18
    POSITIVE LOGITS
    ä½ľæģ¯
    0.22
    缩çŁŃ
    0.21
    addGroup
    0.21
    éĺ¼
    0.20
     affine
    0.19
    .Automation
    0.19
    -bin
    0.19
    hack
    0.19
    æĺİæĺİ
    0.19
    æŸ
    0.19
    Activations Density 0.047%

    No Known Activations