© 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. 12855
    Prev
    Next
    INDEX
    Explanations

    faith and God

    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
    è¾ĵåĩº
    -0.23
    å°Ħ
    -0.22
    ä¼łæĴŃ
    -0.21
    åĩĢåĮĸ
    -0.21
    æ²¾
    -0.20
    æĪIJåĵģ
    -0.20
    reading
    -0.20
    åĪĿ
    -0.20
    åºĵ
    -0.19
    çģµéŃĤ
    -0.19
    POSITIVE LOGITS
    ä¿¡èµĸ
    0.28
    忧èĻij
    0.26
    忧
    0.23
    å®īåħ¨æĦŁ
    0.23
    æĨĤ
    0.22
    agher
    0.22
    _DECLARE
    0.21
     оÑĤдÑĭÑħ
    0.21
     worry
    0.20
    ä¿¡æīĺ
    0.20
    Activations Density 0.023%

    No Known Activations