© 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. 16082
    Prev
    Next
    INDEX
    Explanations

    insurance companies

    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
    æĪIJå°±æĦŁ
    -0.21
    課
    -0.21
     Proj
    -0.20
    åħĪè¿Ľ
    -0.20
    Conflict
    -0.19
     unc
    -0.19
    åĪĽä¸ļèĢħ
    -0.19
    åĨ²çªģ
    -0.19
    comm
    -0.18
     POT
    -0.18
    POSITIVE LOGITS
    ä¿ĿéĻ©
    0.39
     insurance
    0.35
    ä¿ĿéĻ©åħ¬åı¸
    0.33
    人寿
    0.31
    insurance
    0.31
    çīĮçħ§
    0.29
     Insurance
    0.29
    çIJĨèµĶ
    0.28
    ä¿Ŀè´¹
    0.28
     ÑģÑĤÑĢаÑħ
    0.26
    Activations Density 0.041%

    No Known Activations