© 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. 10885
    Prev
    Next
    INDEX
    Explanations

    wage, ms, copper, CO, Sus, amy, stain

    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
    lest
    -0.20
    ems
    -0.20
    为ä¼ģä¸ļ
    -0.20
    EMS
    -0.19
    è°ĥåĬ¨
    -0.19
     SQLITE
    -0.19
    éné
    -0.19
    ìĤ¬ìĿ´
    -0.18
    ingham
    -0.18
     Odd
    -0.18
    POSITIVE LOGITS
    éļıå¤Ħ
    0.20
    lord
    0.20
    -themed
    0.19
     пÑĢиÑĩ
    0.18
    ç»Ħå§Ķä¼ļ
    0.18
    å¶
    0.17
    æĪļ
    0.17
    privileged
    0.17
    .Toolkit
    0.17
    Toolkit
    0.17
    Activations Density 0.461%

    No Known Activations