© 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. 12962
    Prev
    Next
    INDEX
    Explanations

    giving, charity, philanthropy, altruism

    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
    åĩºåľŁ
    -0.23
    æĶ¹éĿ©åĪĽæĸ°
    -0.21
    åºĸ
    -0.20
    伧
    -0.20
    èĤĩ
    -0.19
     gsi
    -0.19
    约æĿŁ
    -0.19
    çªģåĽ´
    -0.19
    azzi
    -0.19
     Pins
    -0.19
    POSITIVE LOGITS
    æħĪåĸĦ
    0.47
     charity
    0.46
    æįIJèµł
    0.45
     charitable
    0.45
    åħ¬çĽĬ
    0.44
    æįIJ款
    0.43
    åħ¬çĽĬæ´»åĬ¨
    0.43
     donation
    0.42
     charities
    0.41
    æįIJçĮ®
    0.40
    Activations Density 0.147%

    No Known Activations