© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15306
    Prev
    Next
    INDEX
    Explanations

    unicode, artifacts, Q,Enter

    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
    è¡ł
    -0.22
     salopes
    -0.22
    梽
    -0.22
    æ¥Ĵ
    -0.21
    æĥİ
    -0.20
    æµķ
    -0.20
    èĮĥåĨ°
    -0.20
    æīĢæľīæĥħèĬĤ
    -0.20
    elsing
    -0.20
    cka
    -0.20
    POSITIVE LOGITS
    å®ŀçī©
    0.29
    æĿ¥èĩª
    0.28
    çī©åĵģ
    0.27
    éĻĪåĪĹ
    0.25
    å±ķåĵģ
    0.24
    å±ķ示
    0.23
    å±ķ示äºĨ
    0.23
    ä¾Ĩèĩª
    0.23
    å±ķåĩº
    0.23
    åIJĦ種
    0.22
    Activations Density 0.015%

    No Known Activations