© 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. 13114
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    æĮĤ
    -0.20
    aciente
    -0.20
    å¥Ĺ
    -0.19
    æ½ľèĥ½
    -0.19
    说è¿ĩ
    -0.18
    opensource
    -0.18
    éı¡
    -0.18
    ä¹ĭ称
    -0.18
    èĵĦ
    -0.18
    ongoose
    -0.17
    POSITIVE LOGITS
    æ¯Ķèµ·
    0.24
    缸æ¯Ķäºİ
    0.23
     compared
    0.23
    缸æ¯Ķ
    0.21
     whereas
    0.20
    å°ıçĻ½
    0.20
    ket
    0.19
    éĶĢ
    0.19
     пÑĢез
    0.18
    èĤļåŃIJ
    0.18
    Activations Density 0.104%

    No Known Activations