© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 714
    Prev
    Next
    INDEX
    Explanations

    faith and trust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    æŁIJç§į
    -0.35
    æŁIJä¸Ģ
    -0.33
    æŁIJäºĽ
    -0.33
    é¢ĩ为
    -0.28
    æŁIJ个
    -0.28
    æ¶īåıĬ
    -0.27
    ongoose
    -0.27
    åĴĦ
    -0.25
    æŁIJç§įç¨ĭ度
    -0.25
    ä¼¼ä¹İ
    -0.25
    POSITIVE LOGITS
    ä¸ĢåĪĩ
    0.30
     trust
    0.28
    everything
    0.27
    æĺ¯æĪijçļĦ
    0.27
     everything
    0.27
    ä¿¡èµĸ
    0.26
     Trust
    0.25
    æ°¸ä¸į
    0.24
     forever
    0.24
    ainless
    0.24
    Activations Density 0.019%

    No Known Activations