© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58180
    Prev
    Next
    INDEX
    Explanations

    insurance claim policy dollars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åIJįæł¡
    -0.10
    èŃ
    -0.10
    交éĢļ
    -0.09
    obble
    -0.09
    èĨĤ
    -0.09
    æĤ²è§Ĥ
    -0.09
    æıª
    -0.09
    æĶ¹æŃ£
    -0.09
     Guar
    -0.08
     коÑĤоÑĢого
    -0.08
    POSITIVE LOGITS
    ç´¢èµĶ
    0.15
    ä¿ĿéĻ©
    0.15
    çIJĨèµĶ
    0.14
     insurance
    0.14
     claim
    0.13
    insurance
    0.13
    ä¿ĿéĻ©åħ¬åı¸
    0.12
     Insurance
    0.12
    çģ¾
    0.11
    åĩŃè¯ģ
    0.11
    Activations Density 0.203%

    No Known Activations