© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2776
    Prev
    Next
    INDEX
    Explanations

    positive emotions, optimism

    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
    Occurred
    -0.23
    以åĨħ
    -0.23
    éĿĻ
    -0.23
    èĨı
    -0.22
     closer
    -0.22
    ç»ŀ
    -0.22
    èµĦæł¼
    -0.22
     closest
    -0.21
     weapon
    -0.21
    åīĥ
    -0.21
    POSITIVE LOGITS
    å¼ĢæľĹ
    0.43
    æĺİåªļ
    0.38
    欢快
    0.37
    éĺ³åħī
    0.35
     cheerful
    0.35
     uplifting
    0.34
    ä¹IJè§Ĥ
    0.33
     upbeat
    0.32
    æ´»åĬĽ
    0.32
    活泼
    0.31
    Activations Density 0.033%

    No Known Activations