© 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. 10835
    Prev
    Next
    INDEX
    Explanations

    mind, consciousness, thought, feelings

    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
    åħ¨æĹ¥
    -0.20
     undo
    -0.19
    éĺª
    -0.19
    æŃ£ä¹ī
    -0.19
    åķĨçĶ¨
    -0.18
     incub
    -0.18
    åľ¨åħ¨çIJĥ
    -0.18
     Worldwide
    -0.18
    éĤķ
    -0.18
    -commercial
    -0.18
    POSITIVE LOGITS
    èĭįçĻ½
    0.23
    æŀ£
    0.21
    æ§İ
    0.20
    æ§ł
    0.20
    驾
    0.20
    ä½ĵéªĮ
    0.19
    eor
    0.19
    ä¸Ģæīĭ
    0.19
    essional
    0.19
    iros
    0.18
    Activations Density 0.014%

    No Known Activations