© 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. 12829
    Prev
    Next
    INDEX
    Explanations

    individual and official capacities

    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
     ÑģаÑħ
    -0.21
    æĹ©æĻļ
    -0.20
    tere
    -0.20
    èĸ®
    -0.20
    ç²ĺ
    -0.19
    éŃį
    -0.19
    å°±è·Ł
    -0.18
    樽
    -0.18
     Vault
    -0.18
    æīĴ
    -0.18
    POSITIVE LOGITS
    足
    0.22
    åIJĪæ³ķæĿĥçĽĬ
    0.20
    ESA
    0.20
    zik
    0.20
    ä¼łçľŁ
    0.20
    å¹²èѦ
    0.19
    åľ¨æł¡
    0.19
    å¤±çľł
    0.19
     matt
    0.18
    åŃĹåı·
    0.18
    Activations Density 0.046%

    No Known Activations