© 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. 1991
    Prev
    Next
    INDEX
    Explanations

    investment management

    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
    çħ¤æ°Ķ
    -0.27
     vandalism
    -0.27
    Mayor
    -0.27
     Ñģимвол
    -0.26
    pygame
    -0.26
    åĵĤ
    -0.25
    ç²¾ç¥ŀæĸĩæĺİ
    -0.25
     Symbols
    -0.25
    _phone
    -0.25
     phone
    -0.24
    POSITIVE LOGITS
    ç§ģåĭŁ
    0.44
     portfolio
    0.43
    åŁºéĩijç»ıçIJĨ
    0.41
     portfolios
    0.40
    è¿IJä½ľ
    0.38
     Portfolio
    0.37
    æĬķèµĦåŁºéĩij
    0.37
    Portfolio
    0.35
    åŁºéĩij管çIJĨ
    0.35
    æĬķèµĦ
    0.35
    Activations Density 0.037%

    No Known Activations