© 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. 13512
    Prev
    Next
    INDEX
    Explanations

    case identifiers and locations

    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
    (pr
    -0.20
    éģĵåħ·
    -0.18
    -
    -0.18
    äºŃ
    -0.18
    ä¸ĢèĤ¡
    -0.18
     pr
    -0.17
    åĪ¶åĵģ
    -0.17
     Experts
    -0.17
    å¤ĩæ¡Ī
    -0.17
    åĭī
    -0.17
    POSITIVE LOGITS
    夤
    0.19
    æľīç§į
    0.19
     Glasses
    0.18
    åĽ«
    0.17
    åħ¬çĽĬæĢ§
    0.17
    ucci
    0.17
    vais
    0.17
    URY
    0.17
    apolis
    0.16
    é¼ĭ
    0.16
    Activations Density 0.149%

    No Known Activations