© 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. 10699
    Prev
    Next
    INDEX
    Explanations

    financial securities and risk

    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
    è¯Ħè®®
    -0.25
    croft
    -0.22
    enger
    -0.21
    spb
    -0.20
    å¯Ĩ
    -0.20
    itra
    -0.20
    bate
    -0.20
     Hindered
    -0.20
    aoke
    -0.19
    伸åĩº
    -0.19
    POSITIVE LOGITS
    é£İéĻ©
    0.30
     securities
    0.27
    é£İéĻ©ç®¡çIJĨ
    0.26
     helicopt
    0.26
     risk
    0.25
     meltdown
    0.25
     Va
    0.23
     Risk
    0.23
    風éļª
    0.23
     portfolio
    0.23
    Activations Density 0.057%

    No Known Activations