© 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. 11703
    Prev
    Next
    INDEX
    Explanations

    thinking and thinkers

    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
    ity
    -0.24
    ãģ¨ãģĦãģ£ãģ¦
    -0.19
    MENT
    -0.18
    bers
    -0.17
    باس
    -0.17
    人家
    -0.17
    ständ
    -0.16
    ÑĪе
    -0.16
    ments
    -0.16
    æīĭæĮģ
    -0.16
    POSITIVE LOGITS
    ģ
    0.22
    ç¼ľ
    0.18
    èĢħ
    0.17
    èĢħçļĦ
    0.17
    вой
    0.17
    /response
    0.16
    ä¸Ńæŀ¢
    0.16
    åĴĮæĬĢæľ¯
    0.16
    æĹ¥æĬ¥ç¤¾
    0.15
    offee
    0.15
    Activations Density 0.026%

    No Known Activations