© 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. 12794
    Prev
    Next
    INDEX
    Explanations

    thinking about size or scope

    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
    æĹłç¼ĺ
    -0.24
    å¿ĥè¡Ģ
    -0.21
    presso
    -0.20
    ä»ķ
    -0.18
    æī°
    -0.18
    éĤij
    -0.18
    AINED
    -0.18
    å¾ħãģ¡
    -0.18
    azzo
    -0.18
    aille
    -0.18
    POSITIVE LOGITS
    æĢĿç»´
    0.29
     thinking
    0.25
    æĢĿèĢĥ
    0.23
    çľ¼çķĮ
    0.22
    -thinking
    0.22
    æĥ³çĿĢ
    0.22
    æĢĿè·¯
    0.21
    è·³åĩº
    0.21
    éķ¿è¿ľ
    0.21
    æĢĿç»´æĸ¹å¼ı
    0.21
    Activations Density 0.009%

    No Known Activations